© 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. 68245
    Prev
    Next
    INDEX
    Explanations

    aha moments and revelations

    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
    m
    -2.02
    at
    -1.97
    la
    -1.91
    seven
    -1.72
     alguns
    -1.68
    er
    -1.68
     edad
    -1.58
    several
    -1.57
    -
    -1.55
     to
    -1.54
    POSITIVE LOGITS
     Consejos
    2.08
     Nuevas
    1.61
     kullanılan
    1.60
     berbentuk
    1.59
     insights
    1.57
    angkap
    1.55
    蒾
    1.54
    езда
    1.52
    高級
    1.52
    Also
    1.52
    Activations Density 0.013%

    No Known Activations