© 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. 46360
    Prev
    Next
    INDEX
    Explanations

    vivid imagination

    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
    t
    0.99
     on
    0.94
     as
    0.83
     or
    0.79
     an
    0.74
    p
    0.74
    od
    0.70
    g
    0.70
    x
    0.69
     out
    0.68
    POSITIVE LOGITS
    м
    1.01
    '
    0.98
    ש
    0.90
    ので
    0.87
    но
    0.86
    ра
    0.84
    ים
    0.79
    д
    0.78
    ↵
    0.77
    ні
    0.77
    Activations Density 0.001%

    No Known Activations