© 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. 324
    Prev
    Next
    INDEX
    Explanations

    red meat or blood

    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
    ค
    1.55
    <0x8B>
    1.50
    ست
    1.48
     الآخر
    1.41
    <0x80>
    1.39
    <0xAE>
    1.30
    ﺮ
    1.30
    нің
    1.28
    囵
    1.27
    此同时
    1.26
    POSITIVE LOGITS
    s
    1.73
    packed
    1.34
    ים
    1.29
     scrub
    1.24
    ز
    1.23
    ore
    1.20
     πολλ
    1.19
    nesses
    1.15
     trekk
    1.14
    el
    1.13
    Activations Density 0.002%

    No Known Activations