© 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. 3491
    Prev
    Next
    INDEX
    Explanations

    gender and health

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

    possessive followed by noun

    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
    2
    0.48
    آ
    0.47
    ों
    0.45
    tedir
    0.45
    تي
    0.45
    to
    0.44
    s
    0.43
    ز
    0.43
    م
    0.43
    tilde
    0.42
    POSITIVE LOGITS
     생
    0.52
    ン
    0.48
     been
    0.45
    า
    0.44
    ಿಂದ
    0.43
    ન
    0.43
     경우
    0.41
    н
    0.40
     가
    0.39
     compass
    0.39
    Activations Density 0.066%

    No Known Activations