© 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. 8904
    Prev
    Next
    INDEX
    Explanations

    names (common prefixes)

    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
    在
    0.37
    是
    0.35
     be
    0.34
    外
    0.33
    ↵
    0.31
     The
    0.31
    我
    0.30
     velha
    0.29
    م
    0.29
    ↵↵
    0.29
    POSITIVE LOGITS
     मेथड
    0.32
    uous
    0.29
    astrophe
    0.28
    <unused1061>
    0.28
    ority
    0.27
    centaje
    0.27
    Default
    0.27
    Qaeda
    0.26
    жность
    0.26
    $,
    0.25
    Activations Density 0.010%

    No Known Activations