© 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. 22153
    Prev
    Next
    INDEX
    Explanations

    code blocks and structured data delimiters

    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
     In
    -2.11
     Because
    -1.75
    because
    -1.71
     could
    -1.67
     &
    -1.62
     it
    -1.58
    In
    -1.55
    It
    -1.53
     in
    -1.52
     How
    -1.49
    POSITIVE LOGITS
    ächst
    1.64
    テープ
    1.59
    幛
    1.58
    शन
    1.57
    ᠁
    1.56
     podstawie
    1.52
     signes
    1.52
    Costs
    1.48
     Réalisation
    1.48
     diversos
    1.46
    Activations Density 0.006%

    No Known Activations