© 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. 13087
    Prev
    Next
    INDEX
    Explanations

    building floors and levels

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

    vertical position, levels, floors

    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
     पहचानने
    0.45
    鸪
    0.44
    겪
    0.44
    eft
    0.43
     कायद्या
    0.42
     onscreen
    0.42
    पाउंड
    0.42
    क्षात्कार
    0.41
     Сле
    0.41
     व्यक्त
    0.41
    POSITIVE LOGITS
    ชั้น
    0.78
     tầng
    0.77
     étages
    0.77
    樓
    0.76
    楼
    0.74
     upstairs
    0.74
     верх
    0.72
     upper
    0.72
    层
    0.71
    층
    0.71
    Activations Density 0.073%

    No Known Activations