© 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. 77434
    Prev
    Next
    INDEX
    Explanations

    file type and size attributes

    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
    戊
    -0.81
    INSTR
    -0.75
     acert
    -0.72
     Coder
    -0.71
    venu
    -0.69
    negate
    -0.69
    NUR
    -0.68
     beton
    -0.68
    fö
    -0.65
     earthen
    -0.64
    POSITIVE LOGITS
    lastIndex
    0.77
     enhancing
    0.74
    vezető
    0.73
     Gemein
    0.73
    нём
    0.72
    おはよう
    0.71
    ách
    0.71
    OrDefault
    0.70
     subjug
    0.70
     providing
    0.69
    Activations Density 0.033%

    No Known Activations