© 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. 13770
    Prev
    Next
    INDEX
    Explanations

    web page structure

    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
     което
    0.74
    了一个
    0.71
     οποίο
    0.69
     η
    0.67
     возника
    0.67
     следующий
    0.65
     bacter
    0.65
     khususnya
    0.64
    }$(
    0.63
    పాల
    0.61
    POSITIVE LOGITS
     Crunchy
    1.11
    𒋗
    1.02
     pencils
    0.98
    ião
    0.97
    itches
    0.97
    hny
    0.97
    માં
    0.96
    .&
    0.94
    ください
    0.93
    パート
    0.93
    Activations Density 0.017%

    No Known Activations