© 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. 251083
    Prev
    Next
    INDEX
    Explanations

    trade, tickets, PMO, derby, chapter

    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
    al
    0.60
    is
    0.54
     lifecycle
    0.50
    н
    0.50
    as
    0.49
     Manifesto
    0.48
    it
    0.48
     devolution
    0.47
     security
    0.46
     crime
    0.46
    POSITIVE LOGITS
    ometimes
    0.58
     〢
    0.54
    asionally
    0.50
     (),
    0.49
     sø
    0.48
    ızlı
    0.47
     ഒ
    0.47
    nehmen
    0.47
    ifié
    0.47
    ånd
    0.47
    Activations Density 0.001%

    No Known Activations