© 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. 11413
    Prev
    Next
    INDEX
    Explanations

    using suppose

    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
    د
    1.34
    س
    1.06
        
    0.91
    д
    0.85
    دأ
    0.79
    在一个
    0.79
    檚
    0.78
    导致
    0.77
    дів
    0.77
    ی
    0.75
    POSITIVE LOGITS
    IC
    0.92
    X
    0.92
    রা
    0.89
    it
    0.88
    Y
    0.88
    AML
    0.88
    er
    0.86
    AM
    0.84
    RAM
    0.81
    ar
    0.80
    Activations Density 0.002%

    No Known Activations