© 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. 84857
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Descrizione
    -1.48
    футбо
    -1.46
    Documentary
    -1.45
    Tanz
    -1.40
    Oktober
    -1.39
    Procurement
    -1.39
    Debate
    -1.38
    Apothe
    -1.37
    schon
    -1.37
     シルエット
    -1.37
    POSITIVE LOGITS
    You
    1.72
    It
    1.66
     to
    1.61
    If
    1.55
     who
    1.55
     should
    1.52
     know
    1.51
     but
    1.51
     what
    1.49
    但
    1.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.