© 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. 177467
    Prev
    Next
    INDEX
    Explanations

    porch patio balcony deck terraces

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

    balconies, patios, covered areas

    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
    TouchUpInside
    0.48
    丵
    0.46
     داخلی
    0.46
    球面
    0.46
     छोटे
    0.45
     정사각형
    0.45
     गोपनीयता
    0.44
    蓟
    0.44
     गुप्त
    0.44
     پاک
    0.43
    POSITIVE LOGITS
    rami
    0.49
     farmhouse
    0.44
     undermine
    0.42
    ische
    0.41
    /
    0.41
     accorded
    0.41
     dances
    0.41
     unsub
    0.41
     Dances
    0.40
     housework
    0.40
    Activations Density 0.054%

    No Known Activations