© 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. 44691
    Prev
    Next
    INDEX
    Explanations

    deal providing professional services

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

    risks and weaknesses

    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
     Constructors
    0.52
    ’
    0.47
     Holi
    0.46
    ,|
    0.44
     vuoden
    0.44
    舜
    0.44
    (|
    0.42
     空
    0.42
     columnName
    0.42
    每一个
    0.41
    POSITIVE LOGITS
     непосред
    0.50
     precipitated
    0.50
     ஏற
    0.49
     Peng
    0.48
    limiting
    0.47
    ties
    0.47
     उत्पादन
    0.47
     सेट
    0.47
     peeling
    0.46
     ಬಳಕೆ
    0.46
    Activations Density 0.000%

    No Known Activations