© 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. 179137
    Prev
    Next
    INDEX
    Explanations

    sports teams and organizations

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

    code and technical terms

    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
    👗
    0.48
    👙
    0.48
    WhiteBalance
    0.48
    Hotel
    0.47
    établissement
    0.47
    Vintage
    0.46
    珽
    0.46
    Instituto
    0.46
    Pixels
    0.46
    riott
    0.45
    POSITIVE LOGITS
     MP
    0.50
     set
    0.47
    p
    0.47
     mp
    0.47
     puntos
    0.45
     giz
    0.45
     cyt
    0.44
     synchron
    0.44
     paradigma
    0.44
    같
    0.44
    Activations Density 0.000%

    No Known Activations