© 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. 136794
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
    ాన్ని
    0.48
     itself
    0.41
    を超
    0.40
     Kristall
    0.39
    を
    0.38
     자체가
    0.37
    jskiego
    0.37
    !("{:
    0.37
    서를
    0.35
    をし
    0.35
    POSITIVE LOGITS
    नस
    0.40
    ocou
    0.40
    Auch
    0.39
    awks
    0.38
     evanescent
    0.38
    </tfoot>
    0.38
    ując
    0.37
    alous
    0.37
    ราม
    0.37
     sélectionnés
    0.37
    Activations Density 0.020%

    No Known Activations