© 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. 19867
    Prev
    Next
    INDEX
    Explanations

    large potential rewards

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

    ask me, about tuning

    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
    a
    0.87
    an
    0.77
    in
    0.56
    ája
    0.55
    suites
    0.52
    e
    0.50
    o
    0.50
     purely
    0.48
    េះ
    0.48
    oja
    0.48
    POSITIVE LOGITS
     ακόμα
    0.52
     Кри
    0.50
     SCRE
    0.50
     망
    0.50
    
    0.50
     বর্গ
    0.49
     Поли
    0.49
     পারেন
    0.48
     lancéolées
    0.48
     중에
    0.46
    Activations Density 0.000%

    No Known Activations