© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26039
    Prev
    Next
    INDEX
    Explanations

    all of you

    np_acts-logits-general · gemini-2.5-flash-lite

    to all or you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    0.58
    ’
    0.53
    -|
    0.50
    -/
    0.48
    oretical
    0.47
     ossia
    0.46
     Ada
    0.46
     把
    0.46
    bao
    0.45
     or
    0.44
    POSITIVE LOGITS
     proponents
    0.52
     Coefficients
    0.48
    ገ
    0.47
     participants
    0.45
    ారణ
    0.45
    특히
    0.45
    癹
    0.45
    游客
    0.42
     प्रतिभागियों
    0.42
    रा
    0.42
    Activations Density 0.017%

    No Known Activations