© 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. 10-GEMMASCOPE-RES-131K
    7. 128341
    Prev
    Next
    INDEX
    Explanations

    code structure and separators

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

    This neuron does not activate on any of the tokens shown—i.e. it remains effectively off for all examples.

    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
    ia
    -3.09
    ка
    -3.06
    咔嚓
    -2.81
    ו
    -2.77
    ta
    -2.55
    و
    -2.41
     anguish
    -2.39
    io
    -2.36
     cómod
    -2.36
    да
    -2.34
    POSITIVE LOGITS
    婓
    3.34
    ”
    2.88
    presumably
    2.64
    which
    2.63
     WHICH
    2.59
    걔
    2.59
     estampada
    2.25
     zs
    2.25
    ⸒
    2.23
     seno
    2.20
    Activations Density 0.005%

    No Known Activations