© 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. 129041
    Prev
    Next
    INDEX
    Explanations

    html/css properties

    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
     Atención
    -1.60
     blé
    -1.59
    whose
    -1.59
    OOOOOO
    -1.59
     pét
    -1.59
    albeit
    -1.58
     ſever
    -1.54
     puits
    -1.52
     malheur
    -1.52
     fantasma
    -1.52
    POSITIVE LOGITS
     is
    2.16
     in
    2.09
     with
    1.73
     on
    1.66
     from
    1.63
     særlig
    1.62
     октября
    1.61
     by
    1.59
     proporcionar
    1.52
     ноября
    1.49
    Activations Density 0.009%

    No Known Activations