© 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. 29831
    Prev
    Next
    INDEX
    Explanations

    variable declarations and list operations

    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
     وفي
    0.37
     ಹಾಗೂ
    0.36
     Fiziki
    0.36
    sigh
    0.35
    Serialization
    0.34
     및
    0.34
    Existing
    0.34
     சமீப
    0.34
     فِي
    0.34
    <unused326>
    0.34
    POSITIVE LOGITS
    ,
    0.36
     lube
    0.32
     Rose
    0.32
     tahan
    0.32
    ually
    0.31
     gắn
    0.31
    به
    0.30
     tube
    0.30
    මට
    0.30
     Danville
    0.30
    Activations Density 0.336%

    No Known Activations