© 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. 147906
    Prev
    Next
    INDEX
    Explanations

    book and tracking

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

    valuable advice and learning experiences

    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
     propriedade
    0.53
    Universität
    0.52
    𝗕
    0.51
     hydrogenation
    0.50
     orthogonality
    0.50
    ী
    0.50
     ciência
    0.49
     архіви
    0.48
    ཋ
    0.47
    ේ
    0.47
    POSITIVE LOGITS
    oco
    0.46
     Lois
    0.46
    jt
    0.46
     Layer
    0.45
    oxo
    0.45
    Layer
    0.45
     Patron
    0.44
     Gen
    0.43
     Multi
    0.43
     Plains
    0.43
    Activations Density 0.000%

    No Known Activations