© 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. 31-GEMMASCOPE-2-RES-65K
    7. 6445
    Prev
    Next
    INDEX
    Explanations

    ну, Fine, mind the

    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_31_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
    t
    0.62
    j
    0.54
    il
    0.52
    y
    0.49
    population
    0.47
    mena
    0.47
    crc
    0.47
    b
    0.46
    work
    0.46
     spesies
    0.46
    POSITIVE LOGITS
     بدی
    0.50
     тот
    0.48
    冦
    0.45
     정말
    0.44
     ARTS
    0.43
    Вер
    0.43
     PHILLIPS
    0.42
     esclusivamente
    0.42
    зло
    0.41
     вер
    0.41
    Activations Density 0.007%

    No Known Activations