© 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. 79441
    Prev
    Next
    INDEX
    Explanations

    blind or lack of sight

    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
     requestId
    0.47
     mocker
    0.46
     trono
    0.45
    貞
    0.44
    ”;
    0.44
    %";
    0.44
     assertFalse
    0.43
     promulgated
    0.43
    /";
    0.43
     adware
    0.42
    POSITIVE LOGITS
    endre
    0.49
     Blind
    0.43
    盲
    0.43
    <0xE8>
    0.42
    <0xD4>
    0.41
     एंड
    0.41
     Those
    0.41
     Moving
    0.41
    Guys
    0.41
    baiki
    0.40
    Activations Density 0.010%

    No Known Activations