© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 140664
    Prev
    Next
    INDEX
    Explanations

    Let

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     सीटेट
    0.76
     pensamientos
    0.72
    㫴
    0.71
    阅
    0.70
    <unused195>
    0.70
    感觉到
    0.70
     serían
    0.68
     überzeugt
    0.68
    <unused1032>
    0.64
     absol
    0.63
    POSITIVE LOGITS
    י
    1.07
    ي
    1.00
    יות
    0.88
    ে
    0.88
    i
    0.87
    ש
    0.83
    する
    0.81
    ა
    0.81
    l
    0.79
    ר
    0.78
    Activations Density 0.017%

    No Known Activations