© 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. 75275
    Prev
    Next
    INDEX
    Explanations

    woman / female person

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

    calculate area and price

    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
    ки
    0.54
     complejo
    0.51
    魉
    0.50
     costruito
    0.50
     edificio
    0.48
     complesso
    0.47
     কারফিউ
    0.47
     изготовления
    0.46
    activo
    0.46
     artériel
    0.46
    POSITIVE LOGITS
    女
    0.54
    探
    0.44
    Chrys
    0.43
    hips
    0.43
    女子
    0.43
    Mash
    0.42
    Chron
    0.42
    ాత
    0.42
     टक
    0.42
     woman
    0.41
    Activations Density 0.001%

    No Known Activations