© 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. 108883
    Prev
    Next
    INDEX
    Explanations

    license and copyright information

    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
     daughter
    -0.80
    ickory
    -0.79
    rillo
    -0.72
    ARIO
    -0.70
    gadget
    -0.68
    prot
    -0.67
    cyber
    -0.67
    凱
    -0.66
    Gear
    -0.66
    daughter
    -0.66
    POSITIVE LOGITS
    而是
    0.80
     instead
    0.79
    retten
    0.75
     (~
    0.70
    Instead
    0.70
    PHeader
    0.69
    สนใจ
    0.68
    xide
    0.68
     mà
    0.68
    łady
    0.67
    Activations Density 0.054%

    No Known Activations