© 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. 141203
    Prev
    Next
    INDEX
    Explanations

    7-segment display

    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
    a
    0.66
    unakan
    0.52
    ใส่
    0.48
    old
    0.47
     a
    0.46
    aub
    0.46
    於
    0.46
    uland
    0.44
     שמ
    0.44
    ೂರ್ಣ
    0.43
    POSITIVE LOGITS
    navi
    0.61
     været
    0.56
     médic
    0.54
     照明
    0.54
     appren
    0.52
     terminó
    0.51
    Ի
    0.49
     apre
    0.49
     iluminación
    0.49
     envió
    0.49
    Activations Density 0.000%

    No Known Activations