© 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. 41436
    Prev
    Next
    INDEX
    Explanations

    rules, notes, or specific contexts

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

    together, common, shared, all

    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
    ству
    0.49
     uzyska
    0.47
    ента
    0.46
    nię
    0.45
     ά
    0.44
    ря
    0.44
     necesitaba
    0.44
     дозво
    0.44
    ганда
    0.44
     μέσα
    0.43
    POSITIVE LOGITS
    もしくは
    0.47
    あるいは
    0.43
     communism
    0.40
     आएंगे
    0.40
     et
    0.39
     または
    0.39
     Communist
    0.39
    ともに
    0.39
    齊
    0.39
     ceny
    0.38
    Activations Density 0.000%

    No Known Activations