© 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. 8034
    Prev
    Next
    INDEX
    Explanations

    look X in comparison

    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
     is
    -2.23
     of
    -1.84
    <>
    -1.44
     to
    -1.30
    os
    -1.21
     you
    -1.20
     bilhões
    -1.20
    ble
    -1.17
    go
    -1.17
    ,”
    -1.16
    POSITIVE LOGITS
     вернулся
    1.41
    efforts
    1.26
     virtudes
    1.24
     seductive
    1.23
     хоте
    1.21
     μόνο
    1.20
    Hanya
    1.20
     defectos
    1.20
    Hauteur
    1.20
     inadequate
    1.20
    Activations Density 0.033%

    No Known Activations