© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2161
    Prev
    Next
    INDEX
    Explanations

    following punctuation or conjunctions

    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
     bedien
    -1.31
     hvilke
    -1.30
     suscit
    -1.24
    わが
    -1.20
     verlangen
    -1.19
     bumbu
    -1.16
    raeli
    -1.16
    とっても
    -1.16
    rolex
    -1.14
     verminder
    -1.13
    POSITIVE LOGITS
     money
    1.46
     strategy
    1.42
     flowers
    1.42
     analysis
    1.33
     technology
    1.30
     politics
    1.27
     animals
    1.26
     success
    1.23
     education
    1.22
     games
    1.21
    Activations Density 0.033%

    No Known Activations