© 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. 767
    Prev
    Next
    INDEX
    Explanations

    landscape

    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
    s
    1.82
    '
    1.36
    ς
    1.36
    ों
    1.33
    ের
    1.30
     “
    1.29
     ‘
    1.27
     স্টাফ
    1.27
    で
    1.27
     "
    1.21
    POSITIVE LOGITS
     собственно
    1.70
     paisaje
    1.65
     abiert
    1.60
    ни
    1.59
     положения
    1.59
     palju
    1.56
     значительно
    1.55
    циях
    1.54
    ᄄ
    1.52
    يًا
    1.52
    Activations Density 0.020%

    No Known Activations