© 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. 48507
    Prev
    Next
    INDEX
    Explanations

    common sense

    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
    电压
    -0.86
    Ս
    -0.84
     gøre
    -0.82
    bronn
    -0.82
     Genu
    -0.80
    comfortable
    -0.79
    queda
    -0.77
    틀
    -0.77
     PIO
    -0.77
    emény
    -0.76
    POSITIVE LOGITS
     sensible
    3.33
     rational
    3.16
     logical
    3.05
     logic
    2.88
     rationality
    2.78
     reasonable
    2.70
    rational
    2.50
     здра
    2.44
     sane
    2.41
     commons
    2.38
    Activations Density 0.053%

    No Known Activations