© 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. 67111
    Prev
    Next
    INDEX
    Explanations

    positive adjectives followed by nouns

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

    descriptions of people and places

    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
    כל
    0.43
    탤
    0.42
    婴
    0.41
     காலம்
    0.40
     بالاتر
    0.40
    ولی
    0.40
    嬰
    0.40
    resu
    0.39
    intas
    0.39
    ូ
    0.39
    POSITIVE LOGITS
     with
    0.55
     impressive
    0.54
     breezy
    0.52
     stylish
    0.49
     handsome
    0.49
     dreamy
    0.47
     victoire
    0.47
     আকারের
    0.47
     looking
    0.46
     মানের
    0.46
    Activations Density 0.136%

    No Known Activations