© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40055
    Prev
    Next
    INDEX
    Explanations

    explanatory, hypotension, inflow, methyl derivatives

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

    technical or programming-related terminology that includes method names, expressions, and explanatory content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    「
    -3.00
    '
    -2.83
     她
    -2.66
    或
    -2.45
    “
    -2.39
    使用
    -2.36
    是
    -2.36
    ：
    -2.34
    巴黎
    -2.34
     ``
    -2.34
    POSITIVE LOGITS
     We
    3.09
    罴
    2.98
    姈
    2.56
     Besonder
    2.44
    媗
    2.42
    酲
    2.39
    かもしれませんが
    2.39
    驩
    2.36
    只剩
    2.33
    Ꭸ
    2.31
    Activations Density 0.003%

    No Known Activations