© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    spatial localization and amplitude

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

    behavior and changes in quantities

    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
    球队
    0.60
    军队
    0.59
    铁路
    0.58
    荣耀
    0.56
    缮
    0.55
    伟大
    0.54
    监狱
    0.54
    秘书
    0.53
    经纪
    0.53
    乡村
    0.52
    POSITIVE LOGITS
     detected
    0.62
     spectral
    0.60
     adsorbed
    0.58
     observed
    0.58
     gradient
    0.57
     monotonically
    0.56
     approximately
    0.55
     peak
    0.54
     amplitude
    0.54
     linewidth
    0.54
    Activations Density 0.232%

    No Known Activations