© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11188
    Prev
    Next
    INDEX
    Explanations

    describing complex topics

    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_9_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
    ை
    1.11
    cijas
    1.09
    ্পনিক
    0.93
    кнове
    0.92
    ′
    0.91
    м
    0.90
     můžete
    0.89
    й
    0.88
    jeto
    0.87
    inando
    0.87
    POSITIVE LOGITS
    وْ
    0.83
    मुंबई
    0.77
    Ông
    0.75
    갈
    0.75
    侔
    0.74
    あくまで
    0.74
     scand
    0.74
     தெரிவித்த
    0.73
    у
    0.72
     conclus
    0.72
    Activations Density 0.166%

    No Known Activations