© 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. 34-GEMMASCOPE-RES-131K
    7. 63983
    Prev
    Next
    INDEX
    Explanations

    XML namespaces and dates

    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
     Monet
    -0.79
    皰
    -0.75
    发生的
    -0.75
    ium
    -0.72
    isher
    -0.71
     Rubens
    -0.71
     Corde
    -0.71
     counting
    -0.71
     Eternity
    -0.70
     Outback
    -0.70
    POSITIVE LOGITS
    Couple
    0.77
    地道
    0.71
    convention
    0.67
    道
    0.66
    Pads
    0.66
    Telling
    0.65
     dima
    0.65
    īn
    0.64
     صنعتی
    0.63
    ⌡
    0.63
    Activations Density 0.046%

    No Known Activations