© 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. 129296
    Prev
    Next
    INDEX
    Explanations

    lists of things or items

    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
     fondamental
    -0.93
     utiliser
    -0.90
     Sử
    -0.90
    utiliz
    -0.89
    компа
    -0.88
    ПК
    -0.87
    кус
    -0.87
    瘸
    -0.83
     gestes
    -0.83
    Erica
    -0.83
    POSITIVE LOGITS
     other
    1.27
     more
    1.03
     another
    0.98
    other
    0.94
     any
    0.93
     this
    0.87
    瀾
    0.85
    喋
    0.85
     every
    0.83
     varying
    0.77
    Activations Density 0.035%

    No Known Activations