© 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. 69630
    Prev
    Next
    INDEX
    Explanations

    formula names

    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
    rolex
    -1.36
    
    -1.30
     rús
    -1.24
    
    -1.23
    embro
    -1.22
    melissa
    -1.20
    鐧
    -1.20
    describing
    -1.20
    ''');
    -1.20
     verschillende
    -1.20
    POSITIVE LOGITS
     they
    1.45
    Some
    1.31
    They
    1.26
     their
    1.16
    Don
    1.15
    ()
    1.15
    .}
    1.13
    are
    1.11
    These
    1.09
    first
    1.08
    Activations Density 0.297%

    No Known Activations