© 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-65K
    7. 51252
    Prev
    Next
    INDEX
    Explanations

    specialized 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_31_width_65k_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
    ，
    0.60
    (),
    0.59
    $,
    0.54
    ၊
    0.54
    %,
    0.47
    ،
    0.46
    களில்
    0.45
    、
    0.44
     called
    0.44
    ，$
    0.44
    POSITIVE LOGITS
     paž
    0.42
     sugli
    0.42
    hubung
    0.42
     pandémie
    0.41
     こんな
    0.40
     jaj
    0.39
     esophagus
    0.39
     prosciutto
    0.38
     ഇമാ
    0.38
     Tshirt
    0.38
    Activations Density 0.010%

    No Known Activations