© 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. 22-GEMMASCOPE-RES-131K
    7. 26340
    Prev
    Next
    INDEX
    Explanations

    numbers and rankings

    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_22/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
    Taking
    -1.04
     没
    -0.96
     SqlCommand
    -0.96
     with
    -0.94
    xicity
    -0.94
    Almost
    -0.86
     that
    -0.86
     taking
    -0.85
     setengah
    -0.84
    Not
    -0.84
    POSITIVE LOGITS
     astounding
    0.92
     bizarre
    0.90
     quirky
    0.87
    asha
    0.82
     astonishing
    0.82
     unending
    0.81
     Bol
    0.81
     impromptu
    0.81
    anza
    0.80
     luscious
    0.80
    Activations Density 0.014%

    No Known Activations