© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 216882
    Prev
    Next
    INDEX
    Explanations

    social, factual, and conceptual categories

    np_acts-logits-general · gemini-2.5-flash-lite

    instructions for email/writing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unmarried
    0.46
    ))
    0.45
    のではないでしょうか
    0.44
     huge
    0.42
    ille
    0.42
     J
    0.41
     y
    0.41
     dramatically
    0.41
     f
    0.40
    マイクロ
    0.39
    POSITIVE LOGITS
    🍲
    0.50
    ⚉
    0.47
     знаком
    0.47
    versive
    0.46
     సంఘ
    0.46
    PATHS
    0.46
     ఘటన
    0.45
     చిహ్
    0.45
     osmosis
    0.45
     الجدول
    0.45
    Activations Density 0.001%

    No Known Activations