© 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. 105176
    Prev
    Next
    INDEX
    Explanations

    Location names and addresses

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

    following specific punctuation and conjunctions

    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
     povo
    0.47
    功率
    0.45
    プレイヤー
    0.43
     శక్తి
    0.42
    力量
    0.42
     койма
    0.42
    くれる
    0.41
    載
    0.40
     Spieler
    0.40
     จํานวน
    0.40
    POSITIVE LOGITS
    Chang
    0.44
     Verd
    0.44
     Hubert
    0.44
    kapet
    0.43
    fand
    0.43
     fik
    0.42
    σία
    0.42
     to
    0.42
     marketplace
    0.42
    go
    0.41
    Activations Density 0.001%

    No Known Activations