© 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. 24-GEMMASCOPE-2-RES-16K
    7. 2352
    Prev
    Next
    INDEX
    Explanations

    code delimiters and strings

    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_24_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
    ের
    0.93
    s
    0.86
     riguarda
    0.83
     latérales
    0.82
     लकार
    0.80
     পড়িল
    0.80
     yuè
    0.78
    ು
    0.77
     नंबर्स
    0.77
     quelquefois
    0.76
    POSITIVE LOGITS
    ’
    1.08
    '
    1.00
    及
    0.86
    ка
    0.84
    /
    0.82
    о
    0.82
    ing
    0.82
    出
    0.80
    it
    0.80
    性
    0.80
    Activations Density 0.040%

    No Known Activations