© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 79523
    Prev
    Next
    INDEX
    Explanations

    beyond or past limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     firſt
    -0.82
    🈲
    -0.79
    τυχ
    -0.79
     bailarina
    -0.77
     muros
    -0.76
    تے
    -0.76
    rouvez
    -0.75
    ONAUT
    -0.74
    えもん
    -0.74
     asfal
    -0.73
    POSITIVE LOGITS
     beyond
    8.44
    beyond
    6.50
     Beyond
    5.81
    Beyond
    5.72
     BEYOND
    4.59
     past
    4.25
     oltre
    3.59
     além
    3.30
    past
    3.00
     bey
    2.89
    Activations Density 0.267%

    No Known Activations