© 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. 22-GEMMASCOPE-RES-131K
    7. 72665
    Prev
    Next
    INDEX
    Explanations

    java.lang.NoClassDefFoundError, IllegalStateException, sorting

    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_22/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
     ananas
    -1.27
     maroc
    -1.18
     alcool
    -1.15
     ordina
    -1.14
     restaura
    -1.14
     rester
    -1.13
     lycée
    -1.11
     bara
    -1.11
     otel
    -1.11
     rire
    -1.10
    POSITIVE LOGITS
     it
    1.33
    There
    1.23
     There
    1.19
     When
    1.16
     after
    1.13
     there
    1.13
     ....
    1.09
     perdió
    1.07
     What
    1.05
     menyebutkan
    1.05
    Activations Density 0.019%

    No Known Activations