© 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. 78769
    Prev
    Next
    INDEX
    Explanations

    divisibility properties

    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
     Taking
    -0.75
     druid
    -0.73
     Sedan
    -0.72
     apapun
    -0.69
     chond
    -0.69
     Goodness
    -0.69
    Taking
    -0.69
    GIUM
    -0.68
     luyện
    -0.68
     undist
    -0.67
    POSITIVE LOGITS
     xem
    0.75
    ⁰
    0.75
     trá
    0.73
     valt
    0.73
    FREQUENCY
    0.72
    ￡
    0.72
     Freire
    0.72
    handleError
    0.71
    Caleb
    0.71
    lably
    0.71
    Activations Density 0.047%

    No Known Activations