© 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. 217408
    Prev
    Next
    INDEX
    Explanations

    action or relevance

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

    processing technical, legal, or specific subjects

    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
     dependents
    0.52
     seeks
    0.50
     owns
    0.50
     sockets
    0.50
     fixes
    0.48
    s
    0.48
     unsuccessfully
    0.48
    S
    0.48
    rophages
    0.48
     socket
    0.47
    POSITIVE LOGITS
     действие
    0.53
     કાર્ય
    0.52
     مطلب
    0.51
     بسی
    0.50
     συμ
    0.50
     فال
    0.47
     пере
    0.47
     इतनी
    0.46
     את
    0.46
     رفتار
    0.46
    Activations Density 0.000%

    No Known Activations