© 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. 27342
    Prev
    Next
    INDEX
    Explanations

    importance, EU, help, long documents

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

    clear area

    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
    驼
    0.50
    駝
    0.46
    ibraries
    0.42
     principally
    0.42
     =,
    0.42
     無
    0.42
     primarily
    0.40
     northwestern
    0.40
     對
    0.39
     উপমহাদেশ
    0.39
    POSITIVE LOGITS
     sveik
    0.47
    интере
    0.45
     impre
    0.44
    หรือไม่
    0.42
     risque
    0.41
     سوال
    0.41
    ជំងឺ
    0.41
    เจอ
    0.41
    सवाल
    0.40
     اچھی
    0.40
    Activations Density 0.001%

    No Known Activations