© 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. 74281
    Prev
    Next
    INDEX
    Explanations

    able to, justify my, tool that

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

    legal considerations and communication channels

    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
    FORE
    0.49
     Kwan
    0.49
    ള
    0.47
    DETAILS
    0.46
    LAYER
    0.44
    ложено
    0.44
    FROM
    0.44
    LAND
    0.43
     發
    0.43
     LAYER
    0.43
    POSITIVE LOGITS
     pedagogical
    0.54
    ที่ไม่
    0.54
     healing
    0.51
     renormal
    0.50
     unsightly
    0.50
     licenciatura
    0.50
    ;*/
    0.49
     deformity
    0.49
    بیداری
    0.48
     renaissance
    0.48
    Activations Density 0.000%

    No Known Activations