© 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. 175939
    Prev
    Next
    INDEX
    Explanations

    gendered nouns and roles

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

    breakdown, consider, structure, ownership

    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
    an
    0.52
    u
    0.49
    MEAS
    0.45
    UL
    0.45
    }{:
    0.44
    v
    0.44
    )(
    0.43
    confirmed
    0.43
    }$
    0.43
    }$,
    0.43
    POSITIVE LOGITS
     kobiety
    0.50
     łyż
    0.49
    りを
    0.48
     femminile
    0.47
     muškar
    0.46
    いています
    0.44
    みを
    0.44
     महिलाओं
    0.44
    ্ল্ড
    0.44
     mujeres
    0.43
    Activations Density 0.004%

    No Known Activations