© 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. 64181
    Prev
    Next
    INDEX
    Explanations

    programming and shorts

    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
    Mutation
    -0.71
    みそ
    -0.69
     muchas
    -0.68
    digd
    -0.67
    ruary
    -0.65
     любую
    -0.64
    ItemStack
    -0.64
    テレ
    -0.63
    ETERS
    -0.63
    侧
    -0.63
    POSITIVE LOGITS
     cse
    0.71
    lios
    0.71
    shorts
    0.68
    cendo
    0.68
     parseFloat
    0.68
    omma
    0.67
    EINVAL
    0.67
    traffic
    0.66
    INCREMENT
    0.65
    Shorts
    0.65
    Activations Density 0.059%

    No Known Activations