© 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. 57936
    Prev
    Next
    INDEX
    Explanations

    email formats for an Initial. or Name

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

    Everyday tasks or specific functionalities

    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
    a
    0.53
     kosten
    0.49
     specialists
    0.46
     znovu
    0.44
    ー
    0.43
    man
    0.43
     shortcomings
    0.42
     bør
    0.42
    kosten
    0.42
     Stevenson
    0.41
    POSITIVE LOGITS
    οδο
    0.52
    езда
    0.47
    驼
    0.44
     உண்ட
    0.44
    㡴
    0.43
    合物
    0.43
     күз
    0.43
    Ј
    0.43
    便于
    0.42
    стал
    0.42
    Activations Density 0.000%

    No Known Activations