© 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. 57076
    Prev
    Next
    INDEX
    Explanations

    numbers following names and words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Bick
    -0.77
     Aid
    -0.73
    يدي
    -0.71
    onHide
    -0.71
     Wheat
    -0.71
    dataloader
    -0.71
     ensi
    -0.70
     kenapa
    -0.70
     Wig
    -0.69
    اعي
    -0.69
    POSITIVE LOGITS
    Ling
    0.87
     Hira
    0.86
    arkas
    0.85
    winn
    0.84
    FIRST
    0.84
    randint
    0.84
    Mis
    0.84
     miss
    0.81
    LINK
    0.80
     Sint
    0.80
    Activations Density 0.013%

    No Known Activations