© 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. 44837
    Prev
    Next
    INDEX
    Explanations

    calls for

    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
    ov
    1.39
    aid
    1.38
    езде
    1.28
    ação
    1.20
     －
    1.20
    kannya
    1.18
    ierten
    1.17
    onance
    1.16
    dioxide
    1.16
    cı
    1.13
    POSITIVE LOGITS
    ভাবে
    1.20
    די
    1.07
    ని
    1.05
    1.05
    ף
    1.03
    로
    1.02
    ום
    1.02
    니
    1.02
    ছিল
    1.00
    ור
    0.97
    Activations Density 0.003%

    No Known Activations