© 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. 87748
    Prev
    Next
    INDEX
    Explanations

    author saying

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

    avoid stock clichés

    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
    in
    0.50
    ած
    0.49
     withstand
    0.47
    ы
    0.46
     uchun
    0.45
     kanggo
    0.45
     dene
    0.45
     digo
    0.44
     feedstock
    0.44
     ரஷ்ய
    0.44
    POSITIVE LOGITS
    이번
    0.45
     Tomás
    0.44
    љу
    0.41
    änen
    0.41
    ตำบล
    0.40
    同意
    0.40
     Лука
    0.40
    㷅
    0.40
    ['-
    0.40
     Consent
    0.39
    Activations Density 0.000%

    No Known Activations