© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12203
    Prev
    Next
    INDEX
    Explanations

    TypeScript

    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
    м
    3.32
    م
    3.21
    &+
    2.97
    й
    2.91
     Nxe
    2.90
    ্ড
    2.90
    ্স
    2.90
    ER
    2.79
    carbonyl
    2.67
    ર
    2.67
    POSITIVE LOGITS
    வதேச
    3.02
    ⮚
    2.97
     worded
    2.93
    คคล
    2.88
     airway
    2.83
     уравнения
    2.77
    unlike
    2.73
    ष्टाचार
    2.72
    ה
    2.71
    pokemon
    2.70
    Activations Density 0.013%

    No Known Activations