© 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. 10-GEMMASCOPE-RES-131K
    7. 71485
    Prev
    Next
    INDEX
    Explanations

    current number

    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
    𝑈
    -1.70
     снова
    -1.49
    pullover
    -1.44
     cukru
    -1.41
     educativos
    -1.41
     spezi
    -1.38
     erneut
    -1.35
    𝐽
    -1.35
    šiu
    -1.33
     nochmal
    -1.31
    POSITIVE LOGITS
     fêtes
    1.61
     oeuvres
    1.55
     any
    1.47
     such
    1.42
    וּ
    1.38
     BIRTHDAY
    1.36
     затруд
    1.31
    foundland
    1.30
    thirds
    1.28
    ogues
    1.28
    Activations Density 0.009%

    No Known Activations