© 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. 43865
    Prev
    Next
    INDEX
    Explanations

    program identifiers followed by punctuation

    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
     also
    -3.17
     usually
    -2.11
     most
    -2.09
    also
    -1.98
     \
    -1.90
    Also
    -1.84
     також
    -1.73
     undoubtedly
    -1.73
    In
    -1.66
     first
    -1.64
    POSITIVE LOGITS
     ofrecen
    1.84
    tráfico
    1.83
     harán
    1.73
    kadang
    1.68
    齜
    1.66
     soulign
    1.60
     dezelve
    1.60
     sorprender
    1.59
     ayudan
    1.58
     niektor
    1.57
    Activations Density 0.015%

    No Known Activations