© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9973
    Prev
    Next
    INDEX
    Explanations

    self or others

    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
    creator
    0.93
     Прави
    0.91
     '//
    0.88
     ni
    0.88
    orient
    0.85
     anymore
    0.84
    alter
    0.84
    change
    0.83
    ford
    0.83
    idea
    0.82
    POSITIVE LOGITS
     które
    1.61
     WHICH
    1.60
    颇
    1.60
     která
    1.57
    极为
    1.55
     which
    1.55
     cuyas
    1.52
     cuja
    1.51
    頗
    1.50
     التي
    1.50
    Activations Density 0.250%

    No Known Activations