© 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. 57986
    Prev
    Next
    INDEX
    Explanations

    phrases ending in punctuation

    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
     inond
    -1.43
     psychologie
    -1.41
     pleins
    -1.38
     vasi
    -1.30
     brune
    -1.27
    quels
    -1.25
     tradis
    -1.24
     camion
    -1.22
     dagar
    -1.20
     indústria
    -1.20
    POSITIVE LOGITS
     from
    1.35
     if
    1.23
     whose
    1.22
     `
    1.17
     *
    1.16
     management
    1.16
     way
    1.16
    </sub>
    1.16
     not
    1.13
     we
    1.13
    Activations Density 0.107%

    No Known Activations