© 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. 197639
    Prev
    Next
    INDEX
    Explanations

    controller, ensuring protection

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

    potential outcomes and states

    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
    ع
    0.60
    ک
    0.55
    จ
    0.54
    ক
    0.54
    И
    0.54
    Г
    0.53
    ح
    0.53
    Т
    0.52
    ग
    0.52
    ك
    0.50
    POSITIVE LOGITS
    ollah
    0.50
    áver
    0.48
    erne
    0.48
    ähne
    0.46
    aks
    0.45
    ளின்
    0.45
    ashes
    0.45
    ivert
    0.45
    ev
    0.45
    erie
    0.44
    Activations Density 0.000%

    No Known Activations