© 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. 79469
    Prev
    Next
    INDEX
    Explanations

    accepted or revised state

    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
     acudir
    -0.84
     veulent
    -0.80
    涉
    -0.77
     automó
    -0.77
    emde
    -0.77
     eficiencia
    -0.77
     triko
    -0.76
    Kond
    -0.73
    Mí
    -0.73
     pokra
    -0.72
    POSITIVE LOGITS
     accepted
    1.82
     Accepted
    1.63
    Accepted
    1.59
     revision
    1.53
     acceptance
    1.45
     revised
    1.42
    accepted
    1.37
     revisions
    1.36
    revision
    1.30
     received
    1.27
    Activations Density 0.050%

    No Known Activations