© 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. 231939
    Prev
    Next
    INDEX
    Explanations

    activities and contexts

    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
     sadr
    0.49
    泹
    0.49
    ريع
    0.49
    لاع
    0.48
     odnosu
    0.48
    Moj
    0.47
    基督
    0.47
    别
    0.47
     يقول
    0.47
    Santiago
    0.46
    POSITIVE LOGITS
     literally
    0.49
     exponents
    0.46
     Ammonia
    0.46
     Selector
    0.45
     controllable
    0.44
     court
    0.44
     nitride
    0.44
     strictly
    0.43
     subtracting
    0.43
     ξ
    0.42
    Activations Density 0.001%

    No Known Activations