© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59471
    Prev
    Next
    INDEX
    Explanations

    jam and preserves

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects references to fruit preserves and related jam- or jelly-making terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to preserved foods (fruit spreads and pickled condiments), especially in contexts of canning/jars and food preservation processes.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    references to homemade preserves, jams, and jellies in recipes or food-related contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ンダイ
    -0.76
    Gau
    -0.75
    yā
    -0.75
     romaine
    -0.73
    DESCR
    -0.72
    еро
    -0.72
     acos
    -0.71
    ium
    -0.71
    hysema
    -0.70
     PLA
    -0.69
    POSITIVE LOGITS
     jams
    2.42
     jam
    2.31
     preserves
    1.96
     Jams
    1.79
     Jam
    1.65
    jam
    1.63
    Jam
    1.59
     preserve
    1.58
     jamming
    1.52
     Preserve
    1.52
    Activations Density 0.021%

    No Known Activations