© 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. 114137
    Prev
    Next
    INDEX
    Explanations

    unveiled the

    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
     of
    -2.09
     faſt
    -1.70
     anzunehmen
    -1.63
     sinnvoll
    -1.53
     empfohlen
    -1.52
    diğimiz
    -1.48
     phénomènes
    -1.46
     다른
    -1.45
     notwendig
    -1.44
     anspruchs
    -1.44
    POSITIVE LOGITS
     also
    1.82
    </h1>
    1.80
    there
    1.66
    ）　
    1.51
    .}
    1.49
     will
    1.48
    市场的
    1.43
     two
    1.41
     after
    1.40
     essencial
    1.39
    Activations Density 0.000%

    No Known Activations