© 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. 36672
    Prev
    Next
    INDEX
    Explanations

    calling for permits

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

    handles / responsible for

    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
     핵
    0.48
     수가
    0.48
     시간이
    0.45
     badass
    0.45
    폭
    0.45
    첫
    0.44
     lackluster
    0.43
     عدم
    0.42
     방식으로
    0.42
    中で
    0.42
    POSITIVE LOGITS
     Apprentice
    0.50
     Pies
    0.47
     Connection
    0.47
     dawa
    0.46
    ்
    0.46
    اليه
    0.46
     Apprentices
    0.46
     conexão
    0.46
     Reliable
    0.46
    i
    0.46
    Activations Density 0.000%

    No Known Activations