© 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. 106752
    Prev
    Next
    INDEX
    Explanations

    societies, logic, group, attempts, tour

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

    man, not solely

    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
     elegante
    0.52
     onları
    0.51
     variété
    0.50
     elegantes
    0.47
     élég
    0.47
    ⵎ
    0.47
    لمان
    0.46
     توانید
    0.46
     możliwość
    0.45
     فرانس
    0.45
    POSITIVE LOGITS
     exclusively
    0.46
    unlist
    0.45
    且
    0.44
    しかも
    0.43
     WITHOUT
    0.43
    _"
    0.43
     NIL
    0.42
    pattern
    0.42
     LIST
    0.42
     BETWEEN
    0.42
    Activations Density 0.003%

    No Known Activations