© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 95840
    Prev
    Next
    INDEX
    Explanations

    only followed by noun

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

    user provides content

    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
    <<"\
    0.48
    イメージ
    0.46
    ResponseType
    0.46
    CreateModel
    0.46
     faulted
    0.45
     св
    0.44
    াদান
    0.43
    UserRepository
    0.43
    TL
    0.42
    🏰
    0.42
    POSITIVE LOGITS
    며
    0.52
    전
    0.49
    zed
    0.44
     ವಿದ
    0.44
     ფორ
    0.44
    gom
    0.43
     supremely
    0.42
    론
    0.42
    eternal
    0.41
     cubes
    0.41
    Activations Density 0.000%

    No Known Activations