© 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. 200012
    Prev
    Next
    INDEX
    Explanations

    loan advance

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

    persuade or offering

    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
    <0x88>
    0.48
    льні
    0.48
    י
    0.46
    yama
    0.46
    ną
    0.46
    یز
    0.45
    le
    0.44
    و
    0.44
    ندہ
    0.44
     Nomination
    0.44
    POSITIVE LOGITS
     ACTION
    0.52
    UIT
    0.51
     slats
    0.49
     RESON
    0.46
    ASK
    0.46
     الاساس
    0.45
     wiggle
    0.45
    出一个
    0.44
    👏👏👏👏
    0.44
     ASGI
    0.44
    Activations Density 0.001%

    No Known Activations