© 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
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 7579
    Prev
    Next
    INDEX
    Explanations

    foreign language tokens

    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
     state
    0.69
     people
    0.67
     off
    0.66
    ,
    0.65
     in
    0.64
     early
    0.64
     low
    0.63
     included
    0.63
     often
    0.62
     around
    0.62
    POSITIVE LOGITS
     اخ
    0.80
    percaya
    0.75
    stven
    0.74
    isał
    0.74
    وأ
    0.73
    wała
    0.73
    ických
    0.72
    ń
    0.71
    BufferedReader
    0.71
    drž
    0.70
    Activations Density 0.218%

    No Known Activations