© 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. 232023
    Prev
    Next
    INDEX
    Explanations

    airport, FasTrack, future, listed, vast

    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
     Horn
    0.50
    <blockquote>
    0.46
     Philippine
    0.46
     tempr
    0.43
    老师
    0.43
    suptitle
    0.42
     Thermodynamic
    0.41
    泡
    0.41
     Kah
    0.40
    プレス
    0.40
    POSITIVE LOGITS
    綣
    0.47
    amesh
    0.47
    емо
    0.46
     висо
    0.46
    有個
    0.46
    牘
    0.46
    yaan
    0.45
     wrongdoing
    0.44
     가수
    0.44
     crescere
    0.44
    Activations Density 0.001%

    No Known Activations