© 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. 11829
    Prev
    Next
    INDEX
    Explanations

    name=" attribute in XML

    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
    <bos>
    1.92
     united
    1.88
    谓
    1.88
     bhavanti
    1.82
    ushes
    1.77
     retreating
    1.75
     glance
    1.74
     charmed
    1.74
     NSMutableArray
    1.73
     કર્મ
    1.71
    POSITIVE LOGITS
    م
    1.98
    heartedly
    1.61
     quede
    1.60
    у
    1.53
    op
    1.52
    est
    1.51
    д
    1.50
    я
    1.50
    🅴
    1.49
    am
    1.44
    Activations Density 0.000%

    No Known Activations