© 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. 10-GEMMASCOPE-RES-131K
    7. 6752
    Prev
    Next
    INDEX
    Explanations

    starts but

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     deliciously
    -2.27
    —-
    -2.25
     delightfully
    -2.22
     wondrous
    -2.16
     remarkably
    -2.14
     decidedly
    -2.13
     VERY
    -2.03
     nonchal
    -2.02
     exceedingly
    -2.00
     somewhat
    -1.99
    POSITIVE LOGITS
     and
    2.63
     when
    2.47
     which
    2.42
     whose
    2.20
     without
    2.05
     began
    2.02
     that
    1.91
     during
    1.89
     they
    1.80
     started
    1.73
    Activations Density 0.007%

    No Known Activations