© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5163
    Prev
    Next
    INDEX
    Explanations

    log and print

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    võ
    1.40
    贓
    1.31
    사회
    1.28
    ع
    1.28
     endif
    1.24
    bruk
    1.23
    TODO
    1.22
    검
    1.21
     herk
    1.21
    으나
    1.21
    POSITIVE LOGITS
    enio
    1.15
     domést
    1.14
     Cots
    1.08
     frequency
    1.08
    erst
    1.07
     País
    1.05
    letts
    1.04
     Warsaw
    1.04
    ius
    1.04
     bedding
    1.04
    Activations Density 0.100%

    No Known Activations