© 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. 11789
    Prev
    Next
    INDEX
    Explanations

    code structure or function

    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
     debut
    0.93
    ers
    0.83
     (
    0.80
     debuted
    0.79
     (@
    0.75
     market
    0.74
    ors
    0.73
    ंकी
    0.70
     (“
    0.69
    -
    0.68
    POSITIVE LOGITS
     trứng
    0.94
     coward
    0.93
     treason
    0.90
     onClose
    0.88
    Paciente
    0.87
    irrah
    0.87
     Tayyip
    0.86
    ﺭ
    0.86
    Chicken
    0.85
    <unused2182>
    0.85
    Activations Density 0.000%

    No Known Activations