© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60303
    Prev
    Next
    INDEX
    Explanations

    ensure

    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
    Not in Any Lists

    No Comments

    Negative Logits
    atleta
    -1.60
     Either
    -1.59
    --"
    -1.55
     kleineren
    -1.54
     reinen
    -1.45
     besonderen
    -1.44
     speziellen
    -1.44
     größeren
    -1.43
     entsprechenden
    -1.43
     bestimmten
    -1.43
    POSITIVE LOGITS
     that
    1.82
     who
    1.67
     inaprop
    1.48
    carian
    1.37
     diritti
    1.36
     lakini
    1.34
    ſſel
    1.32
    錒
    1.32
    liest
    1.30
     portátiles
    1.29
    Activations Density 0.012%

    No Known Activations