© 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. 19997
    Prev
    Next
    INDEX
    Explanations

    up article, up everything

    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
    diagn
    0.60
     Psych
    0.60
    зу
    0.58
    반
    0.58
    ᅠ
    0.58
    Loved
    0.58
    粧
    0.58
    紥
    0.56
    తిరే
    0.56
    Aug
    0.56
    POSITIVE LOGITS
     Lt
    0.75
     باقی
    0.71
    মাল
    0.68
     काळात
    0.67
    隋
    0.66
     ret
    0.65
     पर्यटन
    0.65
    TypeValue
    0.65
     massless
    0.65
    carouselExample
    0.65
    Activations Density 0.003%

    No Known Activations