© 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. 101763
    Prev
    Next
    INDEX
    Explanations

    indoor and outdoor features

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

    outdoor and indoor activities

    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
    データ
    0.59
    스
    0.57
    ス
    0.52
     ilişkin
    0.52
    ม
    0.52
     imaju
    0.51
     nadie
    0.49
     terceros
    0.49
    ク
    0.49
     agreement
    0.48
    POSITIVE LOGITS
    outdoor
    0.97
    Indoor
    0.84
    Outdoor
    0.84
     outdoor
    0.83
     Outdoor
    0.81
    indoor
    0.80
    户外
    0.75
     Indoor
    0.72
     indoor
    0.71
     outdoors
    0.70
    Activations Density 0.046%

    No Known Activations