© 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. 204223
    Prev
    Next
    INDEX
    Explanations

    rules, limits, or costs

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

    food or other essentials, new medical policies

    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
     факти
    0.44
     우리의
    0.44
    "]));
    0.44
    舉行
    0.44
    ರವಾಗಿ
    0.44
    这一
    0.44
    转发
    0.42
    writeHead
    0.42
     ততক্ষণ
    0.42
     हाम्रो
    0.42
    POSITIVE LOGITS
    '
    0.50
     terapi
    0.46
     limits
    0.45
    安い
    0.44
    :
    0.44
    едера
    0.43
     rules
    0.42
     Honda
    0.41
     Regeln
    0.41
     restricciones
    0.41
    Activations Density 0.000%

    No Known Activations