© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 62632
    Prev
    Next
    INDEX
    Explanations

    hormone and menopause related changes

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

    menopause and estrogen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Observer
    0.45
    Observers
    0.45
    機場
    0.44
    肚子
    0.44
    弇
    0.43
    机场
    0.42
    戯
    0.42
    葙
    0.41
    observers
    0.41
    邡
    0.41
    POSITIVE LOGITS
     menopause
    0.83
     Hormone
    0.78
     hormone
    0.76
     hormonal
    0.72
     hormon
    0.68
     horm
    0.65
     hormones
    0.65
     Horm
    0.64
    horm
    0.63
    opausal
    0.60
    Activations Density 0.024%

    No Known Activations