© 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. 22-GEMMASCOPE-RES-131K
    7. 16399
    Prev
    Next
    INDEX
    Explanations

    action verbs followed by nouns

    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_22/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
     we
    -1.63
     other
    -1.34
     and
    -1.31
     truly
    -1.16
     all
    -1.15
     our
    -1.15
     each
    -1.13
     here
    -1.09
     elevada
    -1.09
     aquí
    -1.07
    POSITIVE LOGITS
     stili
    1.24
     despi
    1.16
     satisfactor
    1.15
    dateTimePicker
    1.13
    スム
    1.10
    などが
    1.09
     blant
    1.08
     السياس
    1.08
    textura
    1.06
    eded
    1.04
    Activations Density 0.322%

    No Known Activations