© 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. 10931
    Prev
    Next
    INDEX
    Explanations

    Cover with

    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
     Che
    1.11
     Felix
    1.04
     Grou
    1.03
     UB
    1.02
     Sy
    0.98
     Delete
    0.97
    +"/"+
    0.97
     Deleted
    0.95
     Title
    0.95
                              
    0.95
    POSITIVE LOGITS
    ționale
    1.39
    ște
    1.34
    ()}>
    1.31
    vať
    1.30
    වින්
    1.27
    vée
    1.25
     άνθρω
    1.22
     erfahren
    1.20
    året
    1.19
    ণ
    1.19
    Activations Density 0.001%

    No Known Activations