© 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. 788
    Prev
    Next
    INDEX
    Explanations

    Ural Mountains

    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
    tans
    1.81
    िता
    1.79
    殳
    1.77
    עת
    1.60
     guise
    1.58
    ня
    1.55
     carcin
    1.46
     chir
    1.46
    鏉
    1.45
    ້ງ
    1.45
    POSITIVE LOGITS
    у
    2.17
    Рис
    2.03
    regierung
    1.83
    G
    1.80
    লে
    1.79
     altri
    1.78
    BREAK
    1.78
    runners
    1.77
    ।
    1.76
    ic
    1.75
    Activations Density 0.088%

    No Known Activations