© 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. 68551
    Prev
    Next
    INDEX
    Explanations

    locations and circumstances

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

    location words

    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
     São
    0.42
     governments
    0.40
     disminución
    0.40
     haloes
    0.39
     Karo
    0.39
     `-
    0.39
     ventilators
    0.39
     (\<
    0.38
     ندارد
    0.38
     بإ
    0.38
    POSITIVE LOGITS
    そこで
    0.68
     तिथे
    0.67
    在那里
    0.66
     அங்கு
    0.65
     ওখানে
    0.64
     allí
    0.64
     거기
    0.63
     ahí
    0.59
    邂
    0.59
     అక్కడ
    0.58
    Activations Density 0.112%

    No Known Activations