© 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. 5944
    Prev
    Next
    INDEX
    Explanations

    directions, instructions, or usage

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

    shortened skull or explanation

    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
    बीन
    0.52
     STRU
    0.51
     eleições
    0.50
     شدن
    0.49
     Анг
    0.49
    🔨
    0.48
    _{+}+
    0.48
     ఆదాయ
    0.47
    缫
    0.47
     байланы
    0.47
    POSITIVE LOGITS
     world
    0.51
    日付
    0.49
    world
    0.48
    share
    0.48
     worlds
    0.46
    ;"
    0.46
     fenomen
    0.45
     reaction
    0.45
    有没有
    0.45
    સ્
    0.44
    Activations Density 0.000%

    No Known Activations