© 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. 219142
    Prev
    Next
    INDEX
    Explanations

    legal contexts and specific follow-ups

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

    comparisons and relationships

    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
    )";
    0.46
     false
    0.44
    matical
    0.43
    ጊዜ
    0.42
    );\
    0.42
    什么的
    0.40
    aud
    0.39
    洖
    0.39
    escent
    0.38
    াপ
    0.38
    POSITIVE LOGITS
     mujeres
    0.50
     Prosec
    0.50
     ネ
    0.47
    jetas
    0.47
     KYC
    0.46
     LAD
    0.46
     gangsters
    0.46
     investigaciones
    0.45
     proceder
    0.45
     學
    0.45
    Activations Density 0.001%

    No Known Activations