© 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. 208975
    Prev
    Next
    INDEX
    Explanations

    call early

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

    action outcomes and considerations

    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
     Tact
    0.52
    Fifth
    0.49
     Fifth
    0.47
     Bolet
    0.46
     afresh
    0.46
    Bul
    0.44
     Gravity
    0.44
    B
    0.44
     Caball
    0.44
     Bul
    0.43
    POSITIVE LOGITS
     endGame
    0.48
    hydrocèle
    0.48
     égaux
    0.47
     комму
    0.45
     partiellement
    0.44
    他对
    0.44
     escribió
    0.44
     njegove
    0.44
     addSubview
    0.43
     eterna
    0.43
    Activations Density 0.001%

    No Known Activations