© 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. 13950
    Prev
    Next
    INDEX
    Explanations

    image file names and HTML img tags

    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
    lilla
    -1.00
    нце
    -0.95
     to
    -0.93
    ดับ
    -0.93
    strada
    -0.89
     Evaluación
    -0.89
    angere
    -0.88
     olsun
    -0.88
    martre
    -0.87
    livia
    -0.86
    POSITIVE LOGITS
    Centered
    0.89
    centered
    0.87
    🎣
    0.85
    ☺
    0.85
    Frage
    0.85
     firmas
    0.84
     mögliche
    0.82
    헷
    0.81
    Ꮸ
    0.80
    🤜
    0.79
    Activations Density 0.001%

    No Known Activations