© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8726
    Prev
    Next
    INDEX
    Explanations

    explanation, report, dao, technologies

    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_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
    镌
    0.45
    5
    0.44
    ät
    0.44
    Խ
    0.43
     Linguistic
    0.42
    INFE
    0.41
    慑
    0.40
    శా
    0.39
    燃
    0.39
     अगले
    0.39
    POSITIVE LOGITS
     pecans
    0.49
     poin
    0.49
    тук
    0.46
     GTA
    0.46
    via
    0.45
     pods
    0.45
     acrylonitrile
    0.45
     insulation
    0.45
     promos
    0.45
    ಪಟ್ಟ
    0.44
    Activations Density 0.002%

    No Known Activations