© 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. 217271
    Prev
    Next
    INDEX
    Explanations

    global green

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

    definitions and explanations

    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
     కని
    0.56
     في
    0.56
    衲
    0.55
     ም
    0.50
     कंटिन्यू
    0.49
    يده
    0.49
     نظم
    0.49
     නො
    0.48
     مجال
    0.48
    а
    0.48
    POSITIVE LOGITS
     breakdowns
    0.50
     mutations
    0.48
     applications
    0.47
     triglycerides
    0.47
     mert
    0.47
     infusions
    0.46
     applic
    0.46
     hexagon
    0.46
     dui
    0.45
    จักร
    0.45
    Activations Density 0.000%

    No Known Activations