© 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. 6090
    Prev
    Next
    INDEX
    Explanations

    dual sources

    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
     människ
    1.06
     formations
    1.05
     übrigens
    1.04
     insensible
    1.01
     dựa
    1.01
     |_{
    1.00
     alleys
    0.98
    ^+$
    0.98
     unaffected
    0.97
     xiii
    0.97
    POSITIVE LOGITS
     simultaneous
    2.02
     simultaneously
    1.78
     simult
    1.75
     Simultaneous
    1.67
     одновременно
    1.64
    multiple
    1.59
     concurrently
    1.58
     multiple
    1.58
     동시에
    1.53
    同時
    1.49
    Activations Density 0.678%

    No Known Activations