© 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. 7658
    Prev
    Next
    INDEX
    Explanations

    split string into

    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
    ات
    0.95
    지
    0.91
    스
    0.87
    لها
    0.85
    ל
    0.82
    ان
    0.80
    و
    0.80
    ال
    0.79
    ون
    0.79
    سي
    0.78
    POSITIVE LOGITS
     barg
    0.86
    cribed
    0.80
     forth
    0.80
    don
    0.78
    String
    0.76
    dem
    0.75
     ধরেই
    0.74
    irteen
    0.73
    एनए
    0.72
    oze
    0.70
    Activations Density 0.601%

    No Known Activations