© 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. 193506
    Prev
    Next
    INDEX
    Explanations

    information concerning

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

    Vitamin information

    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
    roch
    0.49
    barth
    0.45
     ইয়াহিয়া
    0.42
    armor
    0.42
    绽
    0.41
    UserDefaults
    0.40
    incer
    0.40
    亲自
    0.39
    👠
    0.38
    耄
    0.38
    POSITIVE LOGITS
     repression
    0.47
    тивна
    0.46
    ZIONE
    0.43
    ций
    0.43
     contract
    0.42
     enters
    0.42
     defect
    0.42
    𝘸
    0.42
    њу
    0.42
     Docket
    0.42
    Activations Density 0.001%

    No Known Activations