© 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. 251399
    Prev
    Next
    INDEX
    Explanations

    picture with providing

    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
     deterrence
    0.52
    я
    0.50
     reseller
    0.47
    幫
    0.47
     franchising
    0.45
     fiz
    0.44
    ও
    0.44
     workspace
    0.44
     safeguarding
    0.42
     drawdown
    0.42
    POSITIVE LOGITS
    akur
    0.50
    con
    0.47
    ly
    0.46
    cnica
    0.46
     benar
    0.46
    varage
    0.46
    hah
    0.45
    W
    0.45
    altet
    0.45
    Eid
    0.45
    Activations Density 0.004%

    No Known Activations