© 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. 19295
    Prev
    Next
    INDEX
    Explanations

    function descriptions and documentation

    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
    బాటు
    0.89
    rimiento
    0.86
    (−
    0.83
    evším
    0.81
    issen
    0.81
    atici
    0.80
    Parrocchia
    0.80
    ïque
    0.80
     italien
    0.79
    дри
    0.78
    POSITIVE LOGITS
     hysteresis
    0.71
     glob
    0.67
     dear
    0.63
    궁
    0.60
     gł
    0.59
     combinatorial
    0.59
     proportional
    0.58
     or
    0.58
    erweise
    0.58
     alas
    0.55
    Activations Density 0.009%

    No Known Activations