© 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. 156232
    Prev
    Next
    INDEX
    Explanations

    providers, tomatoes

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

    writing and drafting

    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
    舸
    0.54
     télé
    0.53
    plaat
    0.52
    ០
    0.50
    legte
    0.50
    ╔
    0.49
     acheté
    0.49
    ᠴ
    0.49
     tapis
    0.48
     Verbre
    0.48
    POSITIVE LOGITS
    an
    0.50
    intes
    0.46
    on
    0.45
    は
    0.45
    at
    0.44
    book
    0.44
    un
    0.43
    meals
    0.43
    tores
    0.43
    の効果
    0.42
    Activations Density 0.000%

    No Known Activations