© 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. 3541
    Prev
    Next
    INDEX
    Explanations

    after subsequent events

    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
     also
    -1.16
     cokelat
    -1.09
     recently
    -1.07
     a
    -1.03
     Verhalten
    -1.01
    lating
    -1.00
    rowable
    -0.98
    WHAT
    -0.97
     Bedürf
    -0.97
     more
    -0.93
    POSITIVE LOGITS
     knowing
    1.20
     being
    1.16
     the
    1.12
     scrutin
    1.05
     getting
    0.99
     giving
    0.97
     Dalai
    0.96
    際は
    0.94
     prolong
    0.94
    чники
    0.93
    Activations Density 0.055%

    No Known Activations