© 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. 73452
    Prev
    Next
    INDEX
    Explanations

    code file beginnings

    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_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
     from
    -2.20
    ">
    -1.97
     who
    -1.84
     $
    -1.82
    2
    -1.80
    B
    -1.75
    I
    -1.73
     for
    -1.68
    From
    -1.68
    An
    -1.64
    POSITIVE LOGITS
    här
    1.69
    岨
    1.65
     diseñadores
    1.57
     salvajes
    1.53
    advised
    1.52
    CHREIB
    1.52
     semblent
    1.50
     gouttes
    1.50
     innumer
    1.49
    ⎔
    1.49
    Activations Density 0.001%

    No Known Activations