© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66262
    Prev
    Next
    INDEX
    Explanations

    baseline examination

    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_22/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
     bemer
    -1.00
     sensação
    -0.96
     lembrar
    -0.90
     vorliegenden
    -0.88
     perceber
    -0.88
     suspensão
    -0.87
     lande
    -0.86
     preços
    -0.86
     discussão
    -0.85
     altes
    -0.85
    POSITIVE LOGITS
     conson
    0.78
     puja
    0.75
     ihnen
    0.75
     wakes
    0.74
     jusque
    0.73
     cura
    0.72
    rzost
    0.71
     Läng
    0.71
     Rapport
    0.71
     दृ
    0.71
    Activations Density 0.026%

    No Known Activations