© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 37959
    Prev
    Next
    INDEX
    Explanations

    supported by

    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
    ット
    1.67
    ان
    1.42
    ッタ
    1.42
    dır
    1.38
     tainted
    1.32
     salivary
    1.32
    瓏
    1.31
    𒆠
    1.30
    Azur
    1.27
     👀
    1.26
    POSITIVE LOGITS
    il
    1.87
    uk
    1.84
    b
    1.69
    id
    1.66
    v
    1.63
    ac
    1.63
     Supported
    1.61
    é
    1.61
    ap
    1.58
    ut
    1.57
    Activations Density 0.059%

    No Known Activations