© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75429
    Prev
    Next
    INDEX
    Explanations

    data subject rights

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

    spelling and sound-alike variations

    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
    덫
    0.46
     célébr
    0.43
    歷
    0.43
    綗
    0.43
     époque
    0.42
    Ջ
    0.42
    曉
    0.41
     rôle
    0.40
    SPECIAL
    0.40
    ン
    0.40
    POSITIVE LOGITS
    urrection
    0.47
     सरकार
    0.45
    yang
    0.44
     genellikle
    0.44
    andha
    0.43
    向けの
    0.43
    icket
    0.43
    ica
    0.42
    ().
    0.42
    的应用
    0.41
    Activations Density 0.000%

    No Known Activations