© 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. 899
    Prev
    Next
    INDEX
    Explanations

    words following "an"

    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
    U
    0.77
    W
    0.75
    0.68
    I
    0.66
    F
    0.66
    ্কার
    0.65
    ный
    0.64
    ările
    0.63
    V
    0.63
    A
    0.61
    POSITIVE LOGITS
     pleadings
    0.75
     pellets
    0.73
     amu
    0.68
     mozzarella
    0.67
     cassettes
    0.66
    ס
    0.66
     novels
    0.66
     banknotes
    0.66
    ح
    0.66
     nucleons
    0.66
    Activations Density 0.854%

    No Known Activations