© 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. 45043
    Prev
    Next
    INDEX
    Explanations

    control method, signal, or circuits

    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
    '
    -2.45
    s
    -2.28
    ’
    -2.27
    2
    -2.19
    …
    -1.90
    "
    -1.85
    e
    -1.81
    (
    -1.80
     He
    -1.79
    1
    -1.70
    POSITIVE LOGITS
    ):
    2.08
    iempos
    1.95
     kancel
    1.87
     Universidades
    1.82
    ÉE
    1.82
    
    1.81
    voer
    1.80
     magnitud
    1.73
    ítani
    1.73
     pokoje
    1.73
    Activations Density 0.067%

    No Known Activations