© 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. 45163
    Prev
    Next
    INDEX
    Explanations

    sigmoid, colon medical procedures

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

    technical or medical terms related to anatomy, particularly focusing on terms like "sigmoid" and programming terms like "softmax".

    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
     This
    -2.08
     When
    -1.98
     boast
    -1.88
     Only
    -1.86
    ዌ
    -1.85
     provincias
    -1.84
    跖
    -1.82
     joys
    -1.80
     серый
    -1.79
     availa
    -1.77
    POSITIVE LOGITS
    2
    2.64
    3
    2.48
    0
    2.44
    ౬
    2.19
    1
    2.13
    6
    2.11
    the
    1.91
    tifies
    1.87
    ,”
    1.87
    5
    1.86
    Activations Density 0.001%

    No Known Activations