© 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. 135882
    Prev
    Next
    INDEX
    Explanations

    operations and occurrences

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

    official funding and university tools

    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
     ಮನೆ
    0.51
     खेला
    0.50
     peintre
    0.48
     konnte
    0.47
    Ⲃ
    0.47
    랬
    0.45
     měla
    0.45
     była
    0.45
    幡
    0.44
     BufferedReader
    0.44
    POSITIVE LOGITS
    oran
    0.52
    á
    0.51
    er
    0.49
     upkeep
    0.47
     automation
    0.46
    usen
    0.46
    osis
    0.45
     disruptions
    0.45
    isé
    0.44
    enance
    0.44
    Activations Density 0.001%

    No Known Activations