© 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. 34-GEMMASCOPE-RES-131K
    7. 76620
    Prev
    Next
    INDEX
    Explanations

    software identifiers and licenses

    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_34/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
    ILITY
    -0.81
     grooves
    -0.77
     Cock
    -0.70
     spots
    -0.70
    ITAS
    -0.69
     Yos
    -0.69
     richest
    -0.68
     Linton
    -0.68
    اق
    -0.66
     virginity
    -0.66
    POSITIVE LOGITS
    Gur
    0.66
     Gur
    0.66
     payments
    0.64
     Waikato
    0.64
    setScene
    0.64
     الشرطة
    0.62
    Payments
    0.62
     capitalism
    0.61
    bindings
    0.60
     practice
    0.59
    Activations Density 0.100%

    No Known Activations