© 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. 6836
    Prev
    Next
    INDEX
    Explanations

    home or domestic activities

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

    home and domestic places

    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
    '
    0.37
    foregroundColor
    0.36
    |=
    0.35
     vorne
    0.35
     mé
    0.34
     mê
    0.34
     headings
    0.34
     détour
    0.34
    眸
    0.33
     acquis
    0.33
    POSITIVE LOGITS
     home
    1.01
     घर
    1.00
    home
    0.94
     ಮನೆಯ
    0.91
     گھر
    0.89
    🏡
    0.88
     домаш
    0.86
    🏠
    0.85
     домашних
    0.84
     வீட்டில்
    0.84
    Activations Density 0.186%

    No Known Activations