© 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. 31-GEMMASCOPE-2-RES-16K
    7. 5637
    Prev
    Next
    INDEX
    Explanations

    type specifiers and attributes

    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_31_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
    法
    0.73
    ương
    0.69
    不开
    0.67
    事項
    0.67
    รอบ
    0.66
    ната
    0.66
    𒅀
    0.65
     bersifat
    0.64
    आर
    0.64
    ร
    0.63
    POSITIVE LOGITS
     类型
    1.01
     getType
    0.97
     kelamin
    0.91
     Typed
    0.86
     Typ
    0.85
     typing
    0.83
    Typed
    0.80
     Typing
    0.79
     유형
    0.79
     typed
    0.76
    Activations Density 0.160%

    No Known Activations