© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45423
    Prev
    Next
    INDEX
    Explanations

    distributed with you

    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
    >(&
    -0.84
    HIL
    -0.78
     Khi
    -0.75
    빼
    -0.69
    leece
    -0.69
     調
    -0.68
    hila
    -0.67
    Telegram
    -0.67
     будин
    -0.67
    llu
    -0.66
    POSITIVE LOGITS
    estrian
    0.74
     kap
    0.72
    广告
    0.70
    lj
    0.70
    ifik
    0.65
     Brick
    0.63
     cosmetics
    0.62
     jad
    0.61
    散歩
    0.60
     hornear
    0.60
    Activations Density 0.053%

    No Known Activations