© 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. 174465
    Prev
    Next
    INDEX
    Explanations

    limiting quantities or actions

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

    recursion and inelastic

    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
     Queste
    0.47
     prefixed
    0.44
    titleTextStyle
    0.43
     topRight
    0.43
     UserName
    0.43
    宫
    0.42
     gleich
    0.42
    lerini
    0.41
     chegada
    0.41
     Entfer
    0.41
    POSITIVE LOGITS
    नों
    0.43
    рию
    0.43
    VE
    0.43
    ABS
    0.43
    kfollowers
    0.42
    m
    0.39
    仿
    0.38
    REV
    0.38
    smtb
    0.38
    DR
    0.38
    Activations Density 0.002%

    No Known Activations