© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 20026
    Prev
    Next
    INDEX
    Explanations

    ethnic background or psychosis

    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
     आलम
    0.79
     addNew
    0.75
     γν
    0.74
    ენტის
    0.72
    --;
    0.72
    yectos
    0.70
     tartalmaz
    0.70
     በተ
    0.69
    からも
    0.68
     wrongly
    0.68
    POSITIVE LOGITS
    ac
    0.60
     Free
    0.60
    сима
    0.59
    ButtonGroup
    0.57
    ண
    0.57
    ResponseWriter
    0.57
    fillStyle
    0.57
    Joint
    0.57
    ptide
    0.57
    Free
    0.56
    Activations Density 0.001%

    No Known Activations