© 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. 14393
    Prev
    Next
    INDEX
    Explanations

    news broadcasting

    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
     of
    -1.25
    contentPadding
    -1.06
    更是
    -1.02
    gas
    -0.94
     Konink
    -0.94
     here
    -0.93
    !\!\
    -0.91
     главы
    -0.90
     adopted
    -0.90
    jsonwebtoken
    -0.88
    POSITIVE LOGITS
     momentarily
    1.00
    iriman
    0.99
    áda
    0.95
     stratégie
    0.94
    ASSE
    0.94
     semel
    0.93
    hướng
    0.93
     exportaciones
    0.93
     temporarily
    0.92
    veless
    0.91
    Activations Density 0.018%

    No Known Activations