© 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. 162870
    Prev
    Next
    INDEX
    Explanations

    health and skin care

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

    gender identity and dysphoria

    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
    ’
    0.49
     \
    0.49
     erase
    0.48
     OSI
    0.48
     Mentor
    0.47
     Chu
    0.47
     McMahon
    0.47
     Indem
    0.47
     Ø
    0.46
     Stephen
    0.45
    POSITIVE LOGITS
    даг
    0.51
    attup
    0.49
    चलर्स
    0.48
    adinam
    0.47
    癬
    0.46
    skin
    0.46
     피부
    0.46
    alakip
    0.45
    ailangan
    0.45
     кожи
    0.44
    Activations Density 0.000%

    No Known Activations