© 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. 57938
    Prev
    Next
    INDEX
    Explanations

    javascript object methods

    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
    שמי
    -0.88
    ListAdapter
    -0.82
    シー
    -0.81
    padded
    -0.78
     Additions
    -0.77
     CYTHON
    -0.75
    拆
    -0.73
    indy
    -0.73
    +[
    -0.71
     extraction
    -0.70
    POSITIVE LOGITS
    assign
    1.38
    ({},
    1.13
     voltak
    0.85
    eavour
    0.84
     assign
    0.83
     resultar
    0.77
    Assign
    0.77
    `.`
    0.75
     Assign
    0.74
     assigning
    0.73
    Activations Density 0.014%

    No Known Activations