© 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. 42799
    Prev
    Next
    INDEX
    Explanations

    forum quotes with attribution

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

    questions, quotes, introductions

    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
    спубли
    0.49
    культур
    0.45
    ங்கிணை
    0.45
    district
    0.45
    𝗰
    0.45
    ਫ਼
    0.45
    暴力
    0.45
     பயணி
    0.45
    ंटे
    0.44
    idcoin
    0.44
    POSITIVE LOGITS
     (
    0.49
     Laboratory
    0.47
     대해
    0.46
     J
    0.45
     Hijo
    0.44
     jou
    0.43
     Joko
    0.43
     Hoje
    0.43
     Lecturer
    0.42
    Endian
    0.39
    Activations Density 0.000%

    No Known Activations