© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6022
    Prev
    Next
    INDEX
    Explanations

    receiver, player, catch, wing

    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
    ◐
    0.95
     تعالیٰ
    0.91
    ियल
    0.85
    持續
    0.82
    ☸
    0.80
    seekBar
    0.79
     vampire
    0.79
    の一部
    0.79
    賈
    0.79
    筠
    0.79
    POSITIVE LOGITS
    avier
    0.89
     thơm
    0.89
    iere
    0.87
    aży
    0.86
    inary
    0.86
    ero
    0.82
    er
    0.82
     phép
    0.80
    h
    0.79
    odies
    0.79
    Activations Density 0.001%

    No Known Activations