© 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. 6827
    Prev
    Next
    INDEX
    Explanations

    click followed by a noun

    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
    т
    1.90
     ако
    1.79
    г
    1.75
    ت
    1.71
    yse
    1.70
    פ
    1.62
     Το
    1.61
    ור
    1.57
     lipoproteins
    1.57
     comer
    1.55
    POSITIVE LOGITS
    ání
    1.59
    Clique
    1.49
    𝑪
    1.49
    ून
    1.41
    ている
    1.39
    ian
    1.38
    wür
    1.38
    Clic
    1.38
    ização
    1.38
    ер
    1.37
    Activations Density 0.031%

    No Known Activations