© 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. 94221
    Prev
    Next
    INDEX
    Explanations

    moving forward

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

    scientific facts and technical details

    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
    SPEC
    0.49
    apoptotic
    0.47
    microwave
    0.47
    心的
    0.46
    
    0.46
    slope
    0.46
    observed
    0.45
    тири
    0.45
    puzzle
    0.45
    ทาง
    0.44
    POSITIVE LOGITS
     Restaur
    0.46
     lists
    0.46
     this
    0.45
    łod
    0.44
    흰
    0.44
    dul
    0.44
    ă
    0.44
     internships
    0.43
     precluded
    0.43
     unsus
    0.43
    Activations Density 0.001%

    No Known Activations