© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8557
    Prev
    Next
    INDEX
    Explanations

    if you don't

    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
    \
    -2.00
     was
    -1.88
    .”
    -1.77
    但是在
    -1.77
     same
    -1.75
    </sup>
    -1.72
     both
    -1.71
    但在
    -1.68
     should
    -1.65
     .
    -1.62
    POSITIVE LOGITS
    蟶
    1.76
    
    1.49
    viato
    1.48
    laat
    1.47
    wwww
    1.46
     Teknologi
    1.46
    leggen
    1.45
     observance
    1.45
    но
    1.45
    verter
    1.44
    Activations Density 0.018%

    No Known Activations