© 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. 46563
    Prev
    Next
    INDEX
    Explanations

    Boeing

    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
     as
    1.05
    ার
    0.89
    털
    0.85
    ală
    0.82
    al
    0.80
     карты
    0.78
    。
    0.78
    ﮐ
    0.78
    дық
    0.77
    のス
    0.76
    POSITIVE LOGITS
    il
    1.28
     Denne
    0.83
    ไม่
    0.79
     Disse
    0.79
    Type
    0.77
    ه
    0.77
     Id
    0.76
     abstra
    0.73
     perda
    0.72
     Arqu
    0.72
    Activations Density 0.001%

    No Known Activations