© 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. 129242
    Prev
    Next
    INDEX
    Explanations

    list items after comma

    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
    the
    -1.76
     by
    -1.70
     was
    -1.69
    ),
    -1.66
     it
    -1.65
    their
    -1.55
    they
    -1.55
    The
    -1.54
     make
    -1.44
    ;
    -1.43
    POSITIVE LOGITS
     sabias
    1.76
    gorro
    1.59
    mohon
    1.58
     interwoven
    1.53
     antiguas
    1.53
    bkz
    1.50
     této
    1.48
     cukru
    1.48
    PvB
    1.48
     těchto
    1.47
    Activations Density 0.142%

    No Known Activations