© 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. 10-GEMMASCOPE-RES-131K
    7. 40720
    Prev
    Next
    INDEX
    Explanations

    archival links

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

    The neuron is triggered by the word “archive” (and related archival link contexts).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     if
    -1.99
     you
    -1.80
     where
    -1.66
     them
    -1.66
    ᩠
    -1.63
     any
    -1.60
     with
    -1.60
     misguided
    -1.58
     include
    -1.56
    してます
    -1.55
    POSITIVE LOGITS
     kapture
    2.02
     эту
    1.97
    obviously
    1.94
     miguel
    1.91
     Accueil
    1.91
     эти
    1.91
    鱘
    1.89
    −/−
    1.89
    these
    1.87
    튿
    1.87
    Activations Density 0.000%

    No Known Activations