© 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. 201601
    Prev
    Next
    INDEX
    Explanations

    country names and states

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

    research or knowledge

    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
     junit
    0.55
     dynast
    0.51
     所
    0.50
     类
    0.49
     главным
    0.49
     выво
    0.49
     ū
    0.48
    滈
    0.48
     xix
    0.48
     vorm
    0.48
    POSITIVE LOGITS
    icates
    0.50
    ocrates
    0.47
    щении
    0.46
     मान्यता
    0.45
    mensaje
    0.44
    ති
    0.43
    attering
    0.43
    তাব
    0.42
    тере
    0.42
    сен
    0.42
    Activations Density 0.001%

    No Known Activations