© 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. 229109
    Prev
    Next
    INDEX
    Explanations

    owners and proprietors

    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
    [-
    0.43
    Captcha
    0.43
    darkMode
    0.43
    PrivateKey
    0.43
    Payments
    0.42
    IfExists
    0.42
    FEED
    0.42
    [-\
    0.41
    (,
    0.41
    Permission
    0.41
    POSITIVE LOGITS
     Plant
    0.53
     PLANT
    0.53
     planta
    0.50
     televisi
    0.49
    さまざまな
    0.49
     związ
    0.48
     colet
    0.48
     wọn
    0.48
     nt
    0.47
     forskellige
    0.47
    Activations Density 0.001%

    No Known Activations