© 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. 1337
    Prev
    Next
    INDEX
    Explanations

    management

    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
    الإ
    1.41
    G
    1.35
    ด์
    1.34
    ことにより
    1.32
    がつ
    1.31
    ك
    1.28
    কাতার
    1.27
    ক
    1.26
     Kecamatan
    1.25
    ש
    1.25
    POSITIVE LOGITS
    tu
    1.59
    而言
    1.58
    tos
    1.45
    akat
    1.45
    \;
    1.45
    ますが
    1.45
    犸
    1.43
    ted
    1.42
    tim
    1.42
    tl
    1.41
    Activations Density 0.040%

    No Known Activations