© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 4354
    Prev
    Next
    INDEX
    Explanations

    division calculations and expressions

    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
    蠻
    1.90
     surmounted
    1.89
    짙
    1.86
    ق
    1.83
    一批
    1.81
    <0x80>
    1.80
    FILES
    1.76
    MST
    1.73
    ๗
    1.72
     データ
    1.69
    POSITIVE LOGITS
    dır
    2.20
    sion
    2.06
    ıyla
    1.96
    ligt
    1.86
     poter
    1.84
    at
    1.82
    ielles
    1.77
    c
    1.72
    enquête
    1.70
    i
    1.70
    Activations Density 0.032%

    No Known Activations