© 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. 8316
    Prev
    Next
    INDEX
    Explanations

    endless loops and possibilities

    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
    ב
    1.20
    и
    1.03
    ле
    0.97
    ể
    0.96
    ى
    0.96
    нер
    0.95
    нан
    0.92
    arın
    0.92
    е
    0.92
    ၏
    0.90
    POSITIVE LOGITS
    UN
    0.98
    EL
    0.96
    IL
    0.94
    OS
    0.94
    ES
    0.93
    TS
    0.90
    IP
    0.89
     ク
    0.88
    OP
    0.85
    UP
    0.84
    Activations Density 0.005%

    No Known Activations