© 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. 20676
    Prev
    Next
    INDEX
    Explanations

    locations on the front or outside

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

    outside a boundary

    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
    ದೆ
    0.49
     necesitas
    0.47
     sprung
    0.46
     جدول
    0.42
    ດ້
    0.42
    िरिक्स
    0.41
     সড়কে
    0.41
    倨
    0.41
     иссле
    0.40
     ਲੋ
    0.40
    POSITIVE LOGITS
    t
    0.48
     Palais
    0.44
    Casa
    0.43
     Maison
    0.43
     Casa
    0.42
     جامعة
    0.42
    Houses
    0.42
    Restaurants
    0.42
    Hotel
    0.41
     casa
    0.41
    Activations Density 0.035%

    No Known Activations