© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 51699
    Prev
    Next
    INDEX
    Explanations

    hexadecimal or technical representations

    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
     trataro
    0.35
    <unused1014>
    0.34
     nirvach
    0.34
    innerApiCalls
    0.34
     ditth
    0.33
     جائزے
    0.32
     splike
    0.32
    .??"]
    0.32
     څرنګ
    0.31
     vasena
    0.31
    POSITIVE LOGITS
    ,
    0.46
    en
    0.39
    -
    0.39
     (
    0.38
    *
    0.37
    ar
    0.36
    ;
    0.36
    е
    0.35
    y
    0.35
     -
    0.33
    Activations Density 0.037%

    No Known Activations