© 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. 201649
    Prev
    Next
    INDEX
    Explanations

    country names and places

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

    direction sequence: body parts, geography, or onwards

    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
    ᓲ
    0.44
     разрабаты
    0.43
    캐
    0.43
     разработан
    0.41
    瓯
    0.41
    ENDER
    0.41
    LEV
    0.41
    bien
    0.40
     націона
    0.40
    錢
    0.40
    POSITIVE LOGITS
     thence
    0.49
    "=>
    0.46
     onwards
    0.45
     onward
    0.44
     downwards
    0.42
    変
    0.41
    сії
    0.39
     n
    0.39
     lên
    0.38
    有意
    0.38
    Activations Density 0.043%

    No Known Activations