Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3331
    Prev
    Next
    INDEX
    Explanations

    especially when long

    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_16k_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
    স
    0.93
     assure
    0.91
     ont
    0.88
    ów
    0.88
     tutta
    0.88
     toute
    0.84
    entire
    0.84
    LAY
    0.83
     wy
    0.82
     Lowe
    0.81
    POSITIVE LOGITS
    нің
    0.85
    gfx
    0.81
    ࿔
    0.79
    "]')
    0.78
    clesi
    0.75
    dbContext
    0.75
    infodisc
    0.74
    enfants
    0.73
    xaml
    0.73
    częściej
    0.72
    Activations Density 0.000%

    No Known Activations