© 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. 207833
    Prev
    Next
    INDEX
    Explanations

    time, strengths, freedom

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

    CI/CD pipelines and technical explanations

    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
    墓志
    0.48
    Town
    0.48
    Ye
    0.46
    RA
    0.44
    RI
    0.42
    Vincent
    0.42
    Yah
    0.42
    TRI
    0.42
    ব্রি
    0.42
    }(\
    0.41
    POSITIVE LOGITS
     aufgrund
    0.54
    ोली
    0.52
     disqualified
    0.52
     समिती
    0.52
     municipality
    0.51
     physiotherapy
    0.50
     तुमच्या
    0.50
     एक्सरसाइज
    0.49
     व्यायाम
    0.49
     می‌
    0.48
    Activations Density 0.001%

    No Known Activations