© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48787
    Prev
    Next
    INDEX
    Explanations

    importance on, influence on, known as, might be

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

    The neuron fires on subjective, evaluative terms—especially adjectives and nouns that convey emphasis or judgment (e.g. critical, importance, drab, especially).

    oai_token-act-pair · o4-miniTriggered 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
     primarily
    -0.90
    getS
    -0.87
     specifically
    -0.83
    Aktual
    -0.82
     möglicherweise
    -0.81
     occasionally
    -0.81
     successivamente
    -0.81
     essential
    -0.80
    ütten
    -0.80
     jewe
    -0.80
    POSITIVE LOGITS
     _
    0.83
    ore
    0.82
    冢
    0.81
    beit
    0.79
    mand
    0.76
     või
    0.76
    横に
    0.75
     kum
    0.75
    lan
    0.74
     eller
    0.73
    Activations Density 0.012%

    No Known Activations