© 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. 61889
    Prev
    Next
    INDEX
    Explanations

    indexed lists

    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
     number
    0.39
    |
    0.39
    제
    0.37
     #(
    0.37
     vj
    0.37
    수
    0.37
    插
    0.37
    ্নে
    0.37
    界
    0.36
    số
    0.36
    POSITIVE LOGITS
     ...
    0.84
    ....
    0.76
     ۔۔۔
    0.71
    \...
    0.71
    ...,
    0.69
     \...
    0.69
    ・・・
    0.68
     ....
    0.68
     ...)
    0.68
    ...
    0.68
    Activations Density 0.080%

    No Known Activations