© 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. 31539
    Prev
    Next
    INDEX
    Explanations

    neural network visualization

    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
    ные
    0.85
    ный
    0.74
    0.74
     больше
    0.73
    ная
    0.72
    OS
    0.71
    뺑
    0.70
    ным
    0.70
    /";
    0.68
     неред
    0.68
    POSITIVE LOGITS
    یس
    0.93
    選手権
    0.82
    Ги
    0.80
     Scorsese
    0.80
    ometri
    0.79
     Shams
    0.78
    uolo
    0.77
     Eis
    0.76
    یعنی
    0.76
    橢
    0.75
    Activations Density 0.000%

    No Known Activations