© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 168712
    Prev
    Next
    INDEX
    Explanations

    existential or death-related contexts

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

    colour sizes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лі
    0.52
    t
    0.48
    记忆
    0.47
    了一个
    0.46
     커피
    0.46
    TypeOf
    0.46
    a
    0.45
    하
    0.45
    Type
    0.44
    Cogn
    0.44
    POSITIVE LOGITS
    clampsia
    0.54
    囑
    0.50
    च्छेद
    0.46
     antigu
    0.45
     perfe
    0.45
     punctu
    0.44
     इत्या
    0.44
     silenc
    0.44
     ﺍ
    0.44
    闔
    0.44
    Activations Density 0.001%

    No Known Activations