© 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. 67108
    Prev
    Next
    INDEX
    Explanations

    new or current descriptions

    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
     they
    -1.62
    ceased
    -1.52
    signable
    -1.48
     mengucap
    -1.45
    ificantly
    -1.43
     они
    -1.42
     опреде
    -1.40
    珰
    -1.39
    lest
    -1.37
    стюм
    -1.37
    POSITIVE LOGITS
     will
    2.25
     would
    2.11
     \
    1.48
    Your
    1.47
     may
    1.31
     must
    1.31
     had
    1.27
     it
    1.27
     there
    1.23
    さは
    1.23
    Activations Density 0.180%

    No Known Activations