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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 19362
    Prev
    Next
    INDEX
    Explanations

    today, date

    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
    時点で
    0.89
     Etappe
    0.81
     calendar
    0.79
     offenen
    0.77
     calendrier
    0.77
    Narr
    0.76
    િ
    0.76
    Wish
    0.75
    अय
    0.75
     Geschäft
    0.74
    POSITIVE LOGITS
     ([
    0.91
    ⒈
    0.89
    }$&$-
    0.80
    clusive
    0.80
    ✴
    0.80
     [](
    0.78
    cules
    0.78
    ricting
    0.77
     (**
    0.77
     individ
    0.77
    Activations Density 0.008%

    No Known Activations