© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12327
    Prev
    Next
    INDEX
    Explanations

    financials, marketing, or academic terms

    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
     ‘
    1.07
     A
    1.03
    0.96
     “
    0.92
     щ
    0.88
    ровать
    0.87
     writing
    0.83
     .
    0.83
     пала
    0.82
     Alcal
    0.82
    POSITIVE LOGITS
     mandato
    1.51
     nanti
    1.49
     lanjutkan
    1.44
     आजही
    1.44
    inheritDoc
    1.44
    encript
    1.43
     potete
    1.42
     sebagian
    1.41
     apakah
    1.41
     diritto
    1.40
    Activations Density 0.000%

    No Known Activations