© 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. 12075
    Prev
    Next
    INDEX
    Explanations

    fir single, with sides, A job

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

    invent details or sources

    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
    𝙢
    0.60
     исправ
    0.51
     хода
    0.50
    ເວລາ
    0.49
    mt
    0.48
    IO
    0.48
    Request
    0.47
    FullName
    0.46
    chtigt
    0.46
    TIMESTAMP
    0.46
    POSITIVE LOGITS
     spes
    0.44
     foyer
    0.44
     paving
    0.44
     satt
    0.43
     vinegar
    0.43
    ば
    0.43
     temper
    0.42
     wikiHow
    0.42
    वी
    0.42
     del
    0.41
    Activations Density 0.000%

    No Known Activations