© 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. 243016
    Prev
    Next
    INDEX
    Explanations

    process, function, and results

    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
    ž
    0.53
    ci
    0.49
     궁
    0.47
    cted
    0.46
    jin
    0.46
    ︠
    0.45
    č
    0.45
    Ⴊ
    0.45
    编辑
    0.45
    ívne
    0.45
    POSITIVE LOGITS
     decisión
    0.51
     Inbetriebnahme
    0.48
     milioni
    0.45
     eficiencia
    0.44
    وأضاف
    0.43
    гия
    0.42
     funcionamento
    0.41
     impec
    0.41
    வினை
    0.41
     millones
    0.41
    Activations Density 0.000%

    No Known Activations