© 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. 222960
    Prev
    Next
    INDEX
    Explanations

    health restore

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

    start-stop and squeeze

    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
     that
    0.54
     mike
    0.51
     combat
    0.48
     this
    0.47
    ↵↵
    0.47
     thats
    0.47
     astronomy
    0.47
     reactors
    0.46
     Reactors
    0.46
     mail
    0.45
    POSITIVE LOGITS
    ön
    0.51
    ügen
    0.51
    нда
    0.49
     எல்லை
    0.49
    のひとつ
    0.48
     রেলস্ট
    0.48
    рина
    0.46
     нео
    0.46
    льтра
    0.45
    ෞ
    0.45
    Activations Density 0.000%

    No Known Activations