© 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-16K
    7. 10980
    Prev
    Next
    INDEX
    Explanations

    lists and management

    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_16k_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
     सुनो
    0.30
    iszt
    0.30
     fasse
    0.30
    рино
    0.30
    льку
    0.30
     TokenType
    0.30
    будь
    0.30
    $\,.
    0.30
    ität
    0.29
     ශ
    0.29
    POSITIVE LOGITS
     z
    0.38
     denen
    0.37
    SUS
    0.36
    Those
    0.36
    ালা
    0.35
    LAH
    0.35
     আছে
    0.34
     leurs
    0.34
    ၣ်
    0.34
    腫
    0.34
    Activations Density 0.229%

    No Known Activations