© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36424
    Prev
    Next
    INDEX
    Explanations

    arrow functions and menu navigation

    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_40_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
    ეც
    0.37
     برخور
    0.36
    耺
    0.36
     மட்டும்
    0.35
     ];
    0.35
    assapi
    0.35
    <0x0C>
    0.34
    "];
    0.34
    ături
    0.34
     distX
    0.34
    POSITIVE LOGITS
     ->
    1.52
     =>
    1.44
    ->
    1.35
    =>
    1.32
     →
    1.28
    →
    1.23
     -->
    1.21
     >
    1.20
    ->"
    1.19
    -->
    1.13
    Activations Density 0.012%

    No Known Activations