© 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. 165314
    Prev
    Next
    INDEX
    Explanations

    connection to, why didn, may contribute, not without

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

    risk appetite, iPhone specifics, provided response, Specialized Support

    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
     naturellement
    0.47
    쑹
    0.46
     clavier
    0.46
     закончи
    0.46
    相続
    0.45
    内容は
    0.45
     organisme
    0.45
     témoins
    0.44
     संरचना
    0.44
     změ
    0.44
    POSITIVE LOGITS
    veless
    0.50
    uty
    0.47
    噘
    0.46
     fears
    0.45
     honom
    0.43
    om
    0.43
    W
    0.43
    pag
    0.42
    Collin
    0.42
     Fears
    0.42
    Activations Density 0.000%

    No Known Activations