© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 9200
    Prev
    Next
    INDEX
    Explanations

    there is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ك
    0.77
    ка
    0.74
    speople
    0.68
    يت
    0.65
    as
    0.63
    ners
    0.62
    فون
    0.61
    me
    0.59
    кать
    0.59
    ng
    0.58
    POSITIVE LOGITS
     një
    0.91
     coś
    0.75
    ના
    0.75
    ル
    0.73
     નામ
    0.73
    ۵
    0.71
     is
    0.71
    ל
    0.71
     něco
    0.70
     możliwość
    0.69
    Activations Density 0.431%

    No Known Activations