© 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. 153010
    Prev
    Next
    INDEX
    Explanations

    Microsoft, MLS, ADR, demand

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

    philosophy, crime, technology

    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
     механи
    0.60
     elektrische
    0.53
     размеров
    0.52
    व
    0.50
    𝙨
    0.50
    وي
    0.50
     mécan
    0.49
     mecánico
    0.49
     ajust
    0.48
    т
    0.48
    POSITIVE LOGITS
     Rainier
    0.45
    ells
    0.44
     Browning
    0.43
    keb
    0.43
     Buf
    0.43
    ceğini
    0.42
    시는
    0.41
    日程
    0.39
    iber
    0.39
     ممکن
    0.39
    Activations Density 0.001%

    No Known Activations