© 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. 78965
    Prev
    Next
    INDEX
    Explanations

    driving off, factories are, open mic

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

    list terminators and separators

    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
    H
    0.46
     اسئله
    0.44
    M
    0.43
    -+
    0.43
    ville
    0.43
    lans
    0.42
    o
    0.42
    UDE
    0.42
     geni
    0.42
    mans
    0.42
    POSITIVE LOGITS
     seria
    0.53
    全ての
    0.51
    一方で
    0.51
     تمامی
    0.48
    νον
    0.47
    জনের
    0.47
    ш
    0.47
    ב
    0.47
     bowiem
    0.47
    matism
    0.46
    Activations Density 0.001%

    No Known Activations