© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 11891
    Prev
    Next
    INDEX
    Explanations

    eyes catching or glued

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     camiseta
    0.86
     shirts
    0.85
    👕
    0.85
     shirt
    0.82
     одежда
    0.79
    Ꮯ
    0.79
     aspirations
    0.79
     activités
    0.79
     animaux
    0.79
    ktir
    0.77
    POSITIVE LOGITS
    ضر
    0.86
    ча
    0.75
    linux
    0.72
    بار
    0.72
    ческие
    0.71
    <unused1839>
    0.70
     Speed
    0.69
    Hall
    0.69
    зде
    0.68
    围
    0.67
    Activations Density 0.000%

    No Known Activations