© 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. 31-GEMMASCOPE-2-RES-262K
    7. 75540
    Prev
    Next
    INDEX
    Explanations

    things inside

    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_31_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
     Kochubei
    0.51
     teşekkür
    0.44
    cinoma
    0.44
    ва
    0.44
    ₕ
    0.44
    ॅ
    0.43
    chis
    0.42
     applauded
    0.41
     Dog
    0.40
    ghum
    0.40
    POSITIVE LOGITS
    órd
    0.43
     vazio
    0.42
     स्टार
    0.41
    冥
    0.40
    erm
    0.40
     térm
    0.39
    ியுள்ளது
    0.39
     fährt
    0.39
    ምት
    0.39
    aments
    0.39
    Activations Density 0.003%

    No Known Activations