© 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. 30845
    Prev
    Next
    INDEX
    Explanations

    "М или Д"

    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
    Однако
    1.79
    너무
    1.66
    Какие
    1.59
    После
    1.52
     Однако
    1.49
    ENSIVE
    1.46
    าร
    1.45
    🏼
    1.45
     enormously
    1.42
    ႈ
    1.41
    POSITIVE LOGITS
    s
    2.16
    t
    1.97
    č
    1.86
    ductory
    1.84
    いた
    1.73
    นี้
    1.73
    𝗮
    1.73
    𝗶
    1.72
    ка
    1.70
    ad
    1.70
    Activations Density 0.005%

    No Known Activations