© 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. 92793
    Prev
    Next
    INDEX
    Explanations

    mathematical forms and variables

    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
     hendes
    -0.81
    Alumni
    -0.81
     Alumni
    -0.81
    疡
    -0.79
    afternoon
    -0.75
     fortæller
    -0.74
    autoIncrement
    -0.73
     Moore
    -0.73
    ┐
    -0.72
    магази
    -0.71
    POSITIVE LOGITS
     α
    1.43
     alpha
    1.28
    alpha
    1.26
     a
    1.26
    a
    1.22
     c
    1.17
    α
    1.14
    CONSTANT
    1.05
     constants
    1.04
     constant
    1.02
    Activations Density 0.135%

    No Known Activations