© 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. 84085
    Prev
    Next
    INDEX
    Explanations

    listen or look

    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
    ၜ
    -1.52
     carapace
    -1.49
     pape
    -1.47
    ítez
    -1.47
     seater
    -1.42
     barnet
    -1.41
    ITY
    -1.41
     boken
    -1.40
     alcun
    -1.39
    ataires
    -1.38
    POSITIVE LOGITS
     rendent
    1.61
     légère
    1.57
    advised
    1.55
    however
    1.48
    новь
    1.46
     puedes
    1.45
     acepta
    1.42
     ír
    1.41
    doub
    1.38
    才行
    1.38
    Activations Density 0.008%

    No Known Activations