© 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. 34-GEMMASCOPE-RES-131K
    7. 63374
    Prev
    Next
    INDEX
    Explanations

    cystic fibrosis or carbon fiber

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

    code and technical abbreviations in parentheses, particularly those containing "CF" or other programming/scientific notation.

    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_34/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
     komunik
    -0.81
     communicated
    -0.76
    ことから
    -0.70
    athered
    -0.70
    偕
    -0.68
     cherries
    -0.68
     konsek
    -0.67
     mantle
    -0.67
    communicate
    -0.66
     Serpent
    -0.65
    POSITIVE LOGITS
     CF
    4.97
    CF
    4.59
     cf
    4.47
    cf
    4.22
     Cf
    3.91
    Cf
    3.69
     CFD
    2.89
     CFM
    2.88
     CFA
    2.88
    CFA
    2.86
    Activations Density 0.042%

    No Known Activations