© 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. 146656
    Prev
    Next
    INDEX
    Explanations

    training or leading

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

    leading way bit along Divide

    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
    后果
    0.50
    _{
    0.47
    ồn
    0.45
    innerHeight
    0.45
    1
    0.45
        
    0.44
     {
    0.44
    E
    0.42
     insidious
    0.41
    Ậ
    0.41
    POSITIVE LOGITS
     பயிற்சி
    0.51
     අපි
    0.47
     شدند
    0.47
     구분
    0.46
     करतात
    0.46
     являются
    0.46
     практика
    0.46
    मार्ग
    0.45
     रास्ते
    0.44
     tantôt
    0.44
    Activations Density 0.009%

    No Known Activations