© 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. 99060
    Prev
    Next
    INDEX
    Explanations

    shipping worldwide

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

    value and related concepts

    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
    <0x94>
    0.50
    сей
    0.49
    тері
    0.49
    rubber
    0.48
    воз
    0.48
    ла
    0.47
    সম্প্র
    0.47
    kara
    0.47
    omin
    0.46
    intelligence
    0.46
    POSITIVE LOGITS
     Consecutive
    0.52
     국
    0.48
     subchapter
    0.48
     Association
    0.46
     Gens
    0.46
     Ü
    0.46
     참여
    0.46
     Write
    0.46
     도
    0.44
     स्की
    0.44
    Activations Density 0.001%

    No Known Activations