© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 214594
    Prev
    Next
    INDEX
    Explanations

    specific nouns and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     *
    0.46
    **
    0.43
    act
    0.42
    clin
    0.42
    *
    0.42
    「
    0.42
     「
    0.40
    复
    0.39
    mate
    0.39
    */
    0.38
    POSITIVE LOGITS
    лесо
    0.46
     ಕಬ್ಬಿಣ
    0.43
    めている
    0.43
    лес
    0.40
     अडानी
    0.39
     小物
    0.39
    駋
    0.39
     PublicKey
    0.38
    ErrorClazz
    0.38
    лото
    0.38
    Activations Density 0.002%

    No Known Activations