© 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. 69356
    Prev
    Next
    INDEX
    Explanations

    former chief, detecting fires, give out

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

    open weights transparency

    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
    ISHED
    0.52
    laşı
    0.49
     fenó
    0.48
     tồn
    0.48
     proib
    0.47
    은
    0.47
     espiritual
    0.46
     estrut
    0.46
     debugShow
    0.45
    꿀
    0.45
    POSITIVE LOGITS
    bald
    0.47
     Silas
    0.47
     Peterson
    0.44
    lander
    0.43
    ccbp
    0.43
    丿
    0.43
     Dryer
    0.42
     dryer
    0.42
     Baltes
    0.42
    帶著
    0.41
    Activations Density 0.001%

    No Known Activations