© 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. 10394
    Prev
    Next
    INDEX
    Explanations

    all the, all of

    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
    </h2>
    -2.67
    this
    -2.11
     correct
    -2.09
     first
    -2.00
     reason
    -1.96
    In
    -1.95
    There
    -1.95
    which
    -1.94
     to
    -1.91
     This
    -1.90
    POSITIVE LOGITS
    </u>
    2.14
     kompatibel
    1.95
     gekocht
    1.91
     parfü
    1.91
    seperti
    1.88
     küm
    1.84
     thoſe
    1.84
    
    1.83
    Waga
    1.83
    ㈲
    1.82
    Activations Density 0.056%

    No Known Activations