© 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. 22-GEMMASCOPE-RES-131K
    7. 73112
    Prev
    Next
    INDEX
    Explanations

    actions or states

    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
     bientôt
    -1.05
    permit
    -0.98
    орты
    -0.98
    まって
    -0.94
     acido
    -0.94
     europa
    -0.91
    いただける
    -0.91
    Cé
    -0.91
     Buscar
    -0.90
    avocat
    -0.90
    POSITIVE LOGITS
     or
    1.17
     scattata
    1.15
     done
    1.07
     prêtres
    1.04
     manually
    1.04
     deciso
    1.01
    Wohn
    0.96
     ufficio
    0.96
    AFFIRMED
    0.94
    setIs
    0.94
    Activations Density 0.017%

    No Known Activations