© 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. 133502
    Prev
    Next
    INDEX
    Explanations

    seriously enjoyed, swift foot

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

    what people achieve

    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
     MFA
    0.48
     P
    0.47
     PLAY
    0.47
     Man
    0.46
     MAN
    0.46
     PhD
    0.46
     Pol
    0.44
     Author
    0.44
     Rick
    0.43
     A
    0.43
    POSITIVE LOGITS
     вертика
    0.54
    SXml
    0.54
    cantidad
    0.52
    메이션
    0.52
    ಿದ
    0.50
    éa
    0.49
    емость
    0.49
    하겠습니다
    0.49
    ສ່ວນ
    0.49
     demás
    0.48
    Activations Density 0.000%

    No Known Activations