© 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. 106204
    Prev
    Next
    INDEX
    Explanations

    cleaning and wiping

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

    descriptions of places and features

    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
    áveis
    0.49
    να
    0.49
    무
    0.49
    ěst
    0.48
    하거나
    0.47
    纳
    0.46
    нес
    0.46
    ável
    0.46
    菇
    0.46
    储
    0.45
    POSITIVE LOGITS
     trp
    0.51
     percolation
    0.50
     Madeleine
    0.49
     subjekt
    0.49
     +,
    0.48
     pergola
    0.48
     ဒ
    0.47
     COR
    0.47
     送料
    0.47
     "*"
    0.46
    Activations Density 0.001%

    No Known Activations