© 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. 1533
    Prev
    Next
    INDEX
    Explanations

    absolute superlatives

    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
    ться
    2.59
    و
    2.16
    م
    1.90
    יא
    1.88
    ির
    1.85
     groin
    1.85
     отлично
    1.80
     reverb
    1.79
    iyê
    1.78
    िनल
    1.75
    POSITIVE LOGITS
    и
    2.33
    ב
    2.13
    ä
    1.85
    لی
    1.77
    І
    1.74
     Reasoning
    1.70
    д
    1.70
    і
    1.70
    ó
    1.69
    з
    1.64
    Activations Density 0.015%

    No Known Activations