© 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. 22-GEMMASCOPE-RES-131K
    7. 27616
    Prev
    Next
    INDEX
    Explanations

    beach volleyball

    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
     Burnt
    -0.82
     Cyc
    -0.80
     estarán
    -0.77
     sabid
    -0.77
     patří
    -0.77
    ério
    -0.75
    ută
    -0.75
    omen
    -0.75
    CLAY
    -0.75
    including
    -0.74
    POSITIVE LOGITS
     other
    0.94
    oires
    0.90
    zji
    0.88
     fhew
    0.88
     obfer
    0.87
    OTHER
    0.87
    komfort
    0.86
     puse
    0.86
    Other
    0.85
     neceff
    0.84
    Activations Density 0.174%

    No Known Activations