© 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. 40-GEMMASCOPE-2-RES-262K
    7. 9652
    Prev
    Next
    INDEX
    Explanations

    accessibility for people with disabilities

    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_40_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
     juicy
    0.49
     promiscu
    0.44
     Juicy
    0.37
     goss
    0.37
    🇾
    0.37
    㕸
    0.37
    作用
    0.36
     booze
    0.36
     blackmail
    0.36
    𒊑
    0.36
    POSITIVE LOGITS
     disability
    2.22
     Disability
    2.16
     disabilities
    1.94
     disabled
    1.87
     Disabilities
    1.87
     wheelchair
    1.84
     discapacidad
    1.83
     инвали
    1.80
     दिव्यांग
    1.79
     Disabled
    1.78
    Activations Density 0.037%

    No Known Activations