© 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. 45005
    Prev
    Next
    INDEX
    Explanations

    CoinGecko, TechCrunch, pengiriman

    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
    ९
    1.84
    र
    1.73
    ८
    1.54
    deki
    1.50
    ný
    1.48
    yyyy
    1.46
    ゃ
    1.46
    २
    1.43
    ्स
    1.41
    من
    1.41
    POSITIVE LOGITS
    ل
    1.85
    ੀਆਂ
    1.80
    ри
    1.76
    ির
    1.72
    ol
    1.69
     raisons
    1.68
     Akufo
    1.66
    ineux
    1.59
    id
    1.55
     Neste
    1.52
    Activations Density 0.003%

    No Known Activations