© 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. 231404
    Prev
    Next
    INDEX
    Explanations

    abundant life

    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
    mite
    0.48
    國家
    0.45
    手術
    0.45
    める
    0.45
     rejest
    0.44
     plabic
    0.44
    し
    0.44
     physiques
    0.44
     ば
    0.44
     inizia
    0.44
    POSITIVE LOGITS
     Khanna
    0.53
     பணியாற்ற
    0.50
     Uns
    0.47
    .")]
    0.45
     afforded
    0.45
    λά
    0.45
     disbanded
    0.45
     Schon
    0.44
    OTP
    0.44
    IJ
    0.43
    Activations Density 0.001%

    No Known Activations