© 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. 26407
    Prev
    Next
    INDEX
    Explanations

    incidents and campaigns

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

    places and contexts

    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
     och
    0.52
     Because
    0.50
     because
    0.49
     These
    0.49
     This
    0.48
     B
    0.47
     this
    0.47
     I
    0.47
     or
    0.46
     You
    0.46
    POSITIVE LOGITS
     unrelenting
    0.55
     допъл
    0.55
    amı
    0.54
     భారీ
    0.54
     демокра
    0.52
    人心
    0.52
     приорите
    0.51
     grueling
    0.51
     unapolog
    0.51
    走进
    0.50
    Activations Density 0.000%

    No Known Activations