© 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
    5. 41-GEMMASCOPE-2-RES-262K
    7. 241458
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    წყვე
    0.57
    鑾
    0.54
    ফো
    0.53
    一组
    0.52
     vẽ
    0.52
     Cathedral
    0.51
    interno
    0.50
    鬯
    0.50
    วาม
    0.50
    addDigit
    0.50
    POSITIVE LOGITS
     paltry
    0.71
     eight
    0.64
     preamble
    0.64
     beş
    0.64
     proclaimed
    0.62
    🖕
    0.62
     пяти
    0.61
     fünf
    0.61
     eighteen
    0.61
     prologue
    0.61
    Activations Density 0.000%

    No Known Activations