© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-65K
    7. 2121
    Prev
    Next
    INDEX
    Explanations

    getting help or information

    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_65k_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
    ка
    0.97
    ك
    0.84
    يك
    0.72
    ту
    0.69
    ”،
    0.68
    пи
    0.67
    пе
    0.66
    вается
    0.66
    widgetTo
    0.65
    ра
    0.64
    POSITIVE LOGITS
    m
    1.11
     on
    1.00
    z
    0.98
    า
    0.91
    d
    0.88
    u
    0.88
    د
    0.88
    ↵↵
    0.88
    ı
    0.86
    b
    0.84
    Activations Density 0.740%

    No Known Activations