© 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. 103718
    Prev
    Next
    INDEX
    Explanations

    all followed by predicate

    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
     Hvis
    -1.36
    ération
    -1.30
     rana
    -1.20
     departament
    -1.18
     lagos
    -1.18
     parten
    -1.18
    ytale
    -1.17
     visualiser
    -1.16
    indahkan
    -1.16
    sobí
    -1.16
    POSITIVE LOGITS
     —
    1.77
     respected
    1.63
     neumáticos
    1.45
    '
    1.45
    見て
    1.43
    řízen
    1.43
     wtedy
    1.42
     trasero
    1.42
     lidé
    1.41
     means
    1.41
    Activations Density 0.015%

    No Known Activations