© 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. 32047
    Prev
    Next
    INDEX
    Explanations

    now, or introductory phrases

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

    accessible and different

    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
    buildSpec
    0.52
     どう
    0.50
    ک
    0.49
     sentidos
    0.47
     えっ
    0.47
    directives
    0.47
     ۲۰۰
    0.47
     cardia
    0.47
    ں
    0.47
    мл
    0.46
    POSITIVE LOGITS
     डालने
    0.47
     kickoff
    0.47
     Num
    0.46
    Wide
    0.45
    Tile
    0.44
     Tile
    0.44
     Nouvelle
    0.44
     Cuts
    0.44
    Num
    0.43
    Meanwhile
    0.43
    Activations Density 0.000%

    No Known Activations