© 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. 223162
    Prev
    Next
    INDEX
    Explanations

    language diversity

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

    physical and sexual aspects

    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
     gages
    0.43
     lå
    0.42
     маршру
    0.42
    闼
    0.41
    ائن
    0.41
     legyen
    0.41
    等级
    0.40
    цы
    0.40
    (!$
    0.40
    لت
    0.40
    POSITIVE LOGITS
    rana
    0.55
     FEEL
    0.52
     ένα
    0.50
    asim
    0.50
     Θ
    0.49
     दौरा
    0.48
     வாழை
    0.48
     KILL
    0.48
    as
    0.47
    ra
    0.47
    Activations Density 0.001%

    No Known Activations