© 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. 16109
    Prev
    Next
    INDEX
    Explanations

    program classes and methods

    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
    Db
    1.04
    ";//
    1.00
     св
    0.99
     sommige
    0.95
    MyDB
    0.94
     plików
    0.93
    ReadToEnd
    0.92
    ڊ
    0.88
     vect
    0.88
    कोई
    0.88
    POSITIVE LOGITS
     title
    0.98
     MHK
    0.97
     presented
    0.94
     ceremony
    0.93
     prefix
    0.91
     Galleries
    0.89
     surname
    0.89
     name
    0.88
     siege
    0.87
     Commander
    0.86
    Activations Density 0.016%

    No Known Activations