© 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. 20042
    Prev
    Next
    INDEX
    Explanations

    identifying specific items or qualities

    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
    Основ
    0.79
     ডেস্ক
    0.79
    த்தான்
    0.77
     hommes
    0.76
     sn
    0.76
     teljesen
    0.76
    傢
    0.76
     ventilated
    0.74
     இருக்க
    0.73
    ंमध्ये
    0.73
    POSITIVE LOGITS
     UUID
    0.84
     स्टार्टअप
    0.83
     señalar
    0.79
     highlighter
    0.78
     объема
    0.78
     राशि
    0.78
     known
    0.78
    脸
    0.77
     quantity
    0.77
    caliber
    0.77
    Activations Density 0.000%

    No Known Activations