© 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. 60173
    Prev
    Next
    INDEX
    Explanations

    action followed by result

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

    business rules

    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
     Alemanha
    0.54
     THOMAS
    0.46
     Ст
    0.46
    വിന്
    0.45
    abilidade
    0.45
     diffused
    0.43
     Lithuania
    0.43
    ט
    0.42
     Volcano
    0.42
     nucleus
    0.42
    POSITIVE LOGITS
    etimes
    0.49
     socializing
    0.48
    写
    0.48
    Posting
    0.47
     определён
    0.47
    这是
    0.47
    ंगामा
    0.46
    k
    0.46
    yaf
    0.45
    정에
    0.45
    Activations Density 0.000%

    No Known Activations