© 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. 47393
    Prev
    Next
    INDEX
    Explanations

    pairs of names and titles

    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
    Not in Any Lists

    No Comments

    Negative Logits
     if
    -1.76
     on
    -1.63
     before
    -1.60
     when
    -1.59
     by
    -1.47
     or
    -1.47
     overtly
    -1.45
     in
    -1.43
     blatantly
    -1.43
     came
    -1.41
    POSITIVE LOGITS
     étudier
    1.38
     erhi
    1.38
     sooo
    1.34
     soooo
    1.32
     verhind
    1.27
     praticamente
    1.22
    なども
    1.18
     tivi
    1.16
     exceptionally
    1.16
     😁
    1.15
    Activations Density 0.001%

    No Known Activations