© 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. 13871
    Prev
    Next
    INDEX
    Explanations

    possible outcomes and choices

    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
    /
    1.59
     pertanto
    1.46
     respectivos
    1.33
     উহার
    1.32
    っております
    1.30
     shall
    1.29
    又は
    1.27
     считаю
    1.25
    であるが
    1.23
     /
    1.22
    POSITIVE LOGITS
     groundbreaking
    2.30
    scientists
    2.23
     researchers
    2.15
    dcsset
    2.12
    <unused276>
    2.12
     nanoparticles
    2.11
    Scientists
    2.06
     scientists
    2.06
    scientist
    2.06
    <unused1408>
    2.06
    Activations Density 0.214%

    No Known Activations