© 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. 30839
    Prev
    Next
    INDEX
    Explanations

    inflammation of

    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
    いた
    1.77
    л
    1.67
    р
    1.64
    сть
    1.56
    з
    1.55
    т
    1.48
    傕
    1.48
    ях
    1.43
    А
    1.42
    ية
    1.36
    POSITIVE LOGITS
    ب
    1.77
    ta
    1.72
    s
    1.66
    دة
    1.63
    tender
    1.54
    ten
    1.46
    the
    1.42
    squareup
    1.40
    corper
    1.38
    temp
    1.36
    Activations Density 0.002%

    No Known Activations