© 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. 200389
    Prev
    Next
    INDEX
    Explanations

    stock market, solid wood, international, constituents, songs, five

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

    political systemfluid mechanicsreversed sentencecreate artAI limitations

    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
    🫶
    0.58
    ிட
    0.55
     कोविड
    0.52
    ใหม่
    0.50
    🥳
    0.50
     प्रिय
    0.50
     ਦੀ
    0.50
    льный
    0.50
     அனைவரும்
    0.49
    新たな
    0.49
    POSITIVE LOGITS
    :
    0.51
     railroads
    0.48
     speculating
    0.47
     croire
    0.46
     corporations
    0.46
     ridiculous
    0.45
     NASDAQ
    0.45
     tetr
    0.45
     washington
    0.44
     quoique
    0.44
    Activations Density 0.000%

    No Known Activations