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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13240
    Prev
    Next
    INDEX
    Explanations

    code implementation, questions"

    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
     harta
    -1.30
     meren
    -1.23
     stres
    -1.16
     saks
    -1.16
    УДК
    -1.11
    Addendum
    -1.11
     flott
    -1.10
     gitar
    -1.09
    perfectly
    -1.08
    Helps
    -1.07
    POSITIVE LOGITS
     you
    1.48
     yourself
    1.26
    you
    1.24
     your
    1.22
     Your
    1.20
     você
    1.13
     You
    1.11
    fxml
    1.07
    ここ
    1.05
     здесь
    1.04
    Activations Density 0.004%

    No Known Activations