© 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. 10931
    Prev
    Next
    INDEX
    Explanations

    and connecting items

    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
    、
    0.47
    ،
    0.46
    及
    0.44
     حصول
    0.44
     例如
    0.43
    ↵↵
    0.43
     hasard
    0.42
     prized
    0.42
     ও
    0.41
    iral
    0.41
    POSITIVE LOGITS
     it
    0.58
     પણ
    0.56
    También
    0.55
    Mapa
    0.55
     таксама
    0.55
    č
    0.54
     there
    0.53
    <unused371>
    0.53
    There
    0.52
    ੜ
    0.52
    Activations Density 0.003%

    No Known Activations