© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65169
    Prev
    Next
    INDEX
    Explanations

    sex hormones and testosterone

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

    words related to hormones, especially sex hormones like estrogen, testosterone, and steroids.

    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
    єм
    -0.92
    Ȉ
    -0.86
     печени
    -0.84
    жидан
    -0.80
     pathogenesis
    -0.79
     PASSWORD
    -0.78
     Utf
    -0.77
    middot
    -0.77
    UnifiedTopology
    -0.77
     getIntent
    -0.76
    POSITIVE LOGITS
     hormones
    3.13
     hormone
    2.75
     hormonal
    2.42
    horm
    2.22
    Horm
    2.17
     Hormones
    2.16
     Hormone
    2.09
     Horm
    1.80
     testosterone
    1.79
     hormon
    1.73
    Activations Density 0.135%

    No Known Activations