© 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. 72679
    Prev
    Next
    INDEX
    Explanations

    quoted or religious phrases

    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
    -0.97
     sûre
    -0.93
     querido
    -0.90
     exitoso
    -0.86
    фор
    -0.85
     kriti
    -0.85
     akci
    -0.84
    bandcamp
    -0.84
     lumineuse
    -0.83
    див
    -0.82
    POSITIVE LOGITS
     환
    0.86
    個室
    0.86
     detta
    0.84
     изменения
    0.84
    entsch
    0.83
    ml
    0.82
    ностью
    0.81
    IVO
    0.80
     urgente
    0.80
    U
    0.80
    Activations Density 0.019%

    No Known Activations