© 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. 8760
    Prev
    Next
    INDEX
    Explanations

    online services or categories

    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
    的
    0.86
    在
    0.81
     كند
    0.78
    نيا
    0.73
    OfString
    0.72
     سي
    0.72
    }');
    0.72
    ۳
    0.71
    𝟑
    0.71
    ول
    0.70
    POSITIVE LOGITS
    a
    1.13
     a
    1.11
    n
    0.98
    p
    0.98
    c
    0.97
    is
    0.93
    e
    0.92
    z
    0.90
    it
    0.88
    ad
    0.87
    Activations Density 0.017%

    No Known Activations