© 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. 217958
    Prev
    Next
    INDEX
    Explanations

    JPDS John occupation

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

    NLU engineer fast updates

    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
    cuts
    0.43
    busters
    0.43
    居
    0.43
    inie
    0.42
    bock
    0.42
    iy
    0.41
    y
    0.41
    clock
    0.41
     }}{\
    0.40
    ARRY
    0.40
    POSITIVE LOGITS
     unsuccessfully
    0.62
     Failed
    0.55
    Έ
    0.52
    ụp
    0.50
     información
    0.49
     Several
    0.47
    എസ്
    0.47
     Έ
    0.47
     Información
    0.47
     forêts
    0.47
    Activations Density 0.001%

    No Known Activations