© 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. 20006
    Prev
    Next
    INDEX
    Explanations

    sustain attention or supersonic flight

    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
    é
    0.91
    -
    0.90
    ся
    0.89
    0
    0.87
    ే
    0.84
    iert
    0.81
    Contributions
    0.80
        
    0.79
    ou
    0.79
    لي
    0.79
    POSITIVE LOGITS
    س
    1.16
    ش
    1.16
    נ
    1.06
    კ
    1.03
    ف
    1.02
    ق
    1.02
    ج
    1.01
    یا
    1.00
    ن
    1.00
    ק
    0.96
    Activations Density 0.019%

    No Known Activations