© 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. 68432
    Prev
    Next
    INDEX
    Explanations

    payment or refund details

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

    Swamp

    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
    fu
    0.48
    á
    0.47
    jä
    0.45
    osphere
    0.45
    tr
    0.44
    뤄
    0.44
    outs
    0.44
    we
    0.43
    രക്ഷ
    0.42
     evol
    0.42
    POSITIVE LOGITS
    也很
    0.47
     également
    0.44
    пределение
    0.43
    也不能
    0.41
    лефон
    0.40
    꽂
    0.40
    也不
    0.39
     গের
    0.39
     refunded
    0.39
    ItemBackground
    0.39
    Activations Density 0.001%

    No Known Activations