© 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. 57635
    Prev
    Next
    INDEX
    Explanations

    male reproductive biology and anatomy

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

    the word "Male" at the beginning of phrases, particularly in scientific or medical contexts.

    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
     of
    -0.97
    もあります
    -0.87
    ]
    -0.85
     पढ़
    -0.79
     alemanes
    -0.77
    NSError
    -0.75
     mũi
    -0.72
     ‘
    -0.72
    这也
    -0.72
    <bos>
    -0.71
    POSITIVE LOGITS
    volent
    1.58
    enhance
    1.09
     enhancement
    1.08
     ♂
    1.05
     Enhancement
    0.99
    imide
    0.95
    branche
    0.92
     OGSÅ
    0.90
    رایی
    0.88
    鉭
    0.88
    Activations Density 0.016%

    No Known Activations