© 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. 10354
    Prev
    Next
    INDEX
    Explanations

    unincorporated community, seeds

    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
     umbro
    -1.94
     diza
    -1.89
     artig
    -1.87
     Pasal
    -1.84
    妧
    -1.81
     citroen
    -1.80
     薬局
    -1.79
     isra
    -1.78
     ragaz
    -1.77
     mauva
    -1.77
    POSITIVE LOGITS
     at
    2.36
     for
    2.14
     some
    2.09
     a
    1.84
     after
    1.71
     not
    1.66
     without
    1.66
     Some
    1.63
     more
    1.61
     einigen
    1.60
    Activations Density 0.163%

    No Known Activations