© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9417
    Prev
    Next
    INDEX
    Explanations

    char arrays

    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
    ále
    1.34
    is
    1.17
     distanza
    1.13
    pero
    1.12
    per
    1.11
    psie
    1.10
    als
    1.09
    i
    1.08
    raff
    1.08
    if
    1.06
    POSITIVE LOGITS
     中央
    1.34
     suspected
    1.32
     nemesis
    1.30
     身
    1.26
     SIDE
    1.26
     GGA
    1.25
     مبار
    1.23
     GAM
    1.23
     경기
    1.23
     STAN
    1.22
    Activations Density 0.000%

    No Known Activations