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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 12636
    Prev
    Next
    INDEX
    Explanations

    gender and personal identity 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
    illaume
    0.47
    ټ
    0.46
    windowActionBar
    0.46
     байланы
    0.45
     automorphisms
    0.44
     पूछे
    0.44
     Vatic
    0.44
     रद्द
    0.43
    ཋ
    0.43
    िशन
    0.43
    POSITIVE LOGITS
    chik
    0.43
     suggest
    0.42
     W
    0.41
     druh
    0.40
     child
    0.40
    pple
    0.40
     étoile
    0.40
     us
    0.39
     aide
    0.39
     kW
    0.39
    Activations Density 0.002%

    No Known Activations