© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8414
    Prev
    Next
    INDEX
    Explanations

    evil, sin, and flaws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    ة
    2.41
     sucesivamente
    1.93
    $\--
    1.77
    、​
    1.77
    "%
    1.75
    ികിത്സ
    1.73
     cheesy
    1.73
    surname
    1.71
    $-
    1.69
    𝐥
    1.68
    POSITIVE LOGITS
    ный
    2.37
    ı
    2.28
    д
    2.21
    и
    2.03
    스러운
    1.98
    дная
    1.98
    te
    1.94
    🟣
    1.93
     Jeder
    1.92
    ጨማሪ
    1.91
    Activations Density 0.297%

    No Known Activations