© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 15264
    Prev
    Next
    INDEX
    Explanations

    code structure and keywords

    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
     прио
    0.80
     rekom
    0.73
     автомобилей
    0.73
    तौर
    0.71
     сі
    0.71
    ᴥ
    0.70
     ហើយ
    0.70
    Thu
    0.69
     respe
    0.69
     জায়গা
    0.68
    POSITIVE LOGITS
    NotNull
    0.71
    װ
    0.64
    Warning
    0.64
    Throw
    0.64
    Thrown
    0.63
     Warning
    0.61
    Check
    0.61
    해도
    0.59
    warning
    0.59
     ਅ
    0.59
    Activations Density 0.002%

    No Known Activations