© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 183003
    Prev
    Next
    INDEX
    Explanations

    language, multilingual texts

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

    levels, context, sung, skin

    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
    Negative Logits
     substitute
    0.54
     substituted
    0.53
     reinforcements
    0.52
     b
    0.50
     substitutions
    0.49
     high
    0.49
     first
    0.48
    st
    0.48
     back
    0.48
     three
    0.48
    POSITIVE LOGITS
     함수의
    0.55
     மொழி
    0.55
     языке
    0.52
    莯
    0.51
    ור
    0.51
    沇
    0.50
    聒
    0.50
     इक्वेशन
    0.49
    栘
    0.49
    彘
    0.48
    Activations Density 0.000%

    No Known Activations