© 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. 225198
    Prev
    Next
    INDEX
    Explanations

    without limiting

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

    punctuation and Spanish verbs

    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
    anje
    0.52
    maxLength
    0.48
    ையிலும்
    0.48
     ‚
    0.47
    barcode
    0.47
    ew
    0.44
    evidence
    0.44
    information
    0.44
    quantitative
    0.43
    𝚗
    0.43
    POSITIVE LOGITS
     Fleur
    0.47
     अद्भ
    0.44
    ⚾
    0.44
     Syr
    0.43
     Crimean
    0.43
    İR
    0.43
     tempos
    0.43
     Utilisez
    0.43
    法语
    0.42
     Nomin
    0.42
    Activations Density 0.001%

    No Known Activations