© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 31662
    Prev
    Next
    INDEX
    Explanations

    leak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ने
    1.61
    ك
    1.57
    كشن
    1.47
    一带
    1.42
     mustered
    1.39
    我看
    1.36
    ב
    1.36
    من
    1.34
    炝
    1.32
    Գ
    1.31
    POSITIVE LOGITS
    iveness
    1.39
    ﺮ
    1.39
     leaks
    1.38
    r
    1.34
    tki
    1.33
    rü
    1.32
    absorption
    1.30
    izu
    1.30
     prazo
    1.30
    arzt
    1.30
    Activations Density 0.011%

    No Known Activations