© 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. 792
    Prev
    Next
    INDEX
    Explanations

    don't just copy

    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
    ма
    0.82
    న
    0.79
    Vendo
    0.76
    ン
    0.73
    Kalau
    0.70
    忑
    0.69
    ن
    0.68
    ी
    0.66
    sa
    0.65
     افز
    0.64
    POSITIVE LOGITS
     imit
    0.85
    r
    0.85
     mula
    0.85
    ר
    0.85
     тысячи
    0.84
     tij
    0.82
    ২
    0.81
    𝘧
    0.78
     Neend
    0.78
     waveguides
    0.76
    Activations Density 0.001%

    No Known Activations