© 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. 177447
    Prev
    Next
    INDEX
    Explanations

    event tickets or items

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

    steampunk

    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
    Тем
    0.49
    VOLUME
    0.48
    त्मा
    0.48
    チナ
    0.46
    рат
    0.46
    Ком
    0.46
    芘
    0.46
    Ку
    0.46
    тва
    0.45
    КУ
    0.45
    POSITIVE LOGITS
    ES
    0.49
    e
    0.49
    E
    0.48
     최
    0.48
     harap
    0.46
    around
    0.46
    es
    0.46
     around
    0.45
     FE
    0.45
     inap
    0.45
    Activations Density 0.001%

    No Known Activations