© 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. 11075
    Prev
    Next
    INDEX
    Explanations

    medicine and legal citations

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

    highway, driving, trends

    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
    VEN
    0.43
    ЕН
    0.41
    TIME
    0.40
    HIDE
    0.39
     lend
    0.38
     ヨ
    0.38
    VICIO
    0.38
     있지만
    0.38
     смотрите
    0.38
    ヨ
    0.38
    POSITIVE LOGITS
    mainframe
    0.42
    ledem
    0.42
     গ্রন্থের
    0.42
    ྜ
    0.41
     gewährle
    0.41
    Ii
    0.40
    defendant
    0.39
    cedures
    0.39
    chapters
    0.38
    gist
    0.38
    Activations Density 0.000%

    No Known Activations