© 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. 381
    Prev
    Next
    INDEX
    Explanations

    demonstrates

    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
    <0x83>
    1.36
    नीकरण
    1.18
    wegen
    1.14
     但是
    1.12
    いった
    1.12
    lerinde
    1.10
    但是在
    1.09
     einzelnen
    1.08
     verrou
    1.08
     其实
    1.06
    POSITIVE LOGITS
    en
    1.57
    ம்
    1.44
    ಾ
    1.43
     Galaxies
    1.42
    ות
    1.38
    ो
    1.38
    ு
    1.38
    ю
    1.33
    де
    1.30
    െ
    1.30
    Activations Density 0.236%

    No Known Activations