© 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. 32678
    Prev
    Next
    INDEX
    Explanations

    reading files and databases

    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
    at
    0.84
     (
    0.80
    (
    0.69
    l
    0.67
    I
    0.67
    v
    0.66
    usepackage
    0.64
    al
    0.61
    lt
    0.59
    alti
    0.59
    POSITIVE LOGITS
    ב
    0.84
    িন
    0.80
    ন
    0.71
     saranno
    0.70
     convertido
    0.70
    ら
    0.70
     cataly
    0.67
    া
    0.67
     mãos
    0.67
    ن
    0.67
    Activations Density 0.002%

    No Known Activations