© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1448
    Prev
    Next
    INDEX
    Explanations

    office decorating, Q:, bacterial colon

    np_acts-logits-general · gemini-2.5-flash-lite

    technical terms and identifiers in programming and technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     endlich
    -0.75
     emis
    -0.74
     Yii
    -0.73
     Infine
    -0.73
     finally
    -0.73
    Ʒ
    -0.71
    greenrobot
    -0.71
     Lebanon
    -0.70
    andang
    -0.70
     viu
    -0.69
    POSITIVE LOGITS
    Toledo
    0.88
    SLC
    0.76
     :
    0.73
     насла
    0.73
     Zuma
    0.73
    jsonString
    0.72
    apia
    0.71
    隆
    0.70
    lopen
    0.70
    ako
    0.70
    Activations Density 0.000%

    No Known Activations