© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17306
    Prev
    Next
    INDEX
    Explanations

    feminine/family concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    疑問
    0.45
    詞
    0.45
    vare
    0.43
    ension
    0.43
    ician
    0.42
    Kiza
    0.42
    찮
    0.42
    Ꮕ
    0.42
    дне
    0.42
    вре
    0.42
    POSITIVE LOGITS
     Wu
    0.47
     Mujeres
    0.47
     rodziny
    0.44
     map
    0.44
     femenino
    0.43
     primero
    0.43
     weib
    0.43
     eq
    0.42
     perl
    0.41
     gels
    0.41
    Activations Density 0.001%

    No Known Activations