© 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. 107117
    Prev
    Next
    INDEX
    Explanations

    .option("property", "value")

    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
     railroad
    -0.79
    StringLen
    -0.79
     Len
    -0.76
    Джере
    -0.67
    爆発
    -0.67
    addElement
    -0.66
    segno
    -0.65
     Откры
    -0.65
    Len
    -0.65
    🟠
    -0.65
    POSITIVE LOGITS
    брю
    0.69
    ברס
    0.68
    rw
    0.67
    "><?=
    0.65
    idxs
    0.65
     isoto
    0.63
     loneliness
    0.63
     biết
    0.63
    dollars
    0.63
     minY
    0.62
    Activations Density 0.058%

    No Known Activations