© 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. 121797
    Prev
    Next
    INDEX
    Explanations

    best hotel

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

    subtracting from online calculations

    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
     bakın
    0.46
    UATION
    0.43
     propre
    0.42
     대체
    0.42
     darbo
    0.41
    ↵
    0.40
     twilight
    0.40
    եց
    0.40
    ored
    0.39
    plugin
    0.39
    POSITIVE LOGITS
    <0x94>
    0.48
    ج
    0.47
    مہ
    0.47
    書館
    0.47
     يحتوي
    0.46
    蘸
    0.46
    圩
    0.46
     تحتوي
    0.45
    IServerGame
    0.45
    協會
    0.45
    Activations Density 0.000%

    No Known Activations