© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 175075
    Prev
    Next
    INDEX
    Explanations

    nonlinear behavior and stiffness

    np_acts-logits-general · gemini-2.5-flash-lite

    thresholded nonlinear activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    designs
    0.46
    全員
    0.46
     desain
    0.46
    DESIGN
    0.45
     एक्सप्ले
    0.45
     антенна
    0.45
     हवे
    0.44
    촐
    0.44
    பட
    0.43
    Designs
    0.43
    POSITIVE LOGITS
     Nonlinear
    0.73
     threshold
    0.68
     nonlinearity
    0.68
     thresholds
    0.65
     Threshold
    0.65
     nonlinear
    0.63
    threshold
    0.61
    Threshold
    0.58
     hysteresis
    0.55
    nonlinear
    0.55
    Activations Density 0.066%

    No Known Activations