© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 7244
    Prev
    Next
    INDEX
    Explanations

    regression or classification models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_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
    唒
    1.47
    漿
    1.46
    ExprNode
    1.45
    老師
    1.44
     parser
    1.40
    ッ
    1.37
    学習
    1.37
    ループ
    1.34
     instructors
    1.34
    DisplayText
    1.33
    POSITIVE LOGITS
     “
    1.07
     Covid
    0.96
     tro
    0.96
     „
    0.95
     Tro
    0.95
    ,“
    0.94
     ca
    0.88
    heits
    0.85
     Ton
    0.85
     Le
    0.84
    Activations Density 0.000%

    No Known Activations