© 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. 174189
    Prev
    Next
    INDEX
    Explanations

    gender, or gendered terms

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

    Factorial, one hole, Internal Tool

    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
     Relationships
    0.52
    ov
    0.46
    7
    0.44
     &
    0.43
     t
    0.43
    ology
    0.43
    jug
    0.42
    VERSE
    0.42
    :
    0.42
    dk
    0.41
    POSITIVE LOGITS
     акчага
    0.54
    되었다
    0.52
    मीर
    0.51
    ರ
    0.49
     competición
    0.48
     použití
    0.48
     ettha
    0.47
    변경된파일명
    0.47
     शनिवार
    0.46
     presentada
    0.46
    Activations Density 0.000%

    No Known Activations