© 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. 10967
    Prev
    Next
    INDEX
    Explanations

    data flow and changes

    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
     zbog
    1.49
    önig
    1.36
     Soto
    1.36
     figsize
    1.34
     když
    1.34
    dote
    1.34
     जेव्हा
    1.31
    姬
    1.31
    ėmis
    1.30
    umis
    1.30
    POSITIVE LOGITS
    Parallel
    1.32
    ">=
    1.23
    ടുത
    1.21
     Prosec
    1.17
    Miscellaneous
    1.14
    Repeating
    1.13
     ا
    1.11
    рак
    1.11
     รัก
    1.11
    दयाल
    1.10
    Activations Density 0.000%

    No Known Activations