© 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. 109337
    Prev
    Next
    INDEX
    Explanations

    outlier detection

    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
    ون
    0.81
    स
    0.73
    ни
    0.66
     POW
    0.64
    نا
    0.62
     Slavic
    0.61
    ό
    0.61
    ஸ்
    0.61
     powied
    0.61
    ur
    0.60
    POSITIVE LOGITS
    '
    1.00
     outlier
    0.94
     outliers
    0.93
    А
    0.74
     interessi
    0.71
    𝐾
    0.71
    Го
    0.70
    ﾍ
    0.70
     exception
    0.68
    Anomaly
    0.68
    Activations Density 0.004%

    No Known Activations