© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 3567
    Prev
    Next
    INDEX
    Explanations

    punctuation and response

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     "
    0.88
     delightfully
    0.77
     `
    0.74
     snugly
    0.74
     répart
    0.73
     даже
    0.73
     Pacífico
    0.72
     `--
    0.71
     *
    0.69
     often
    0.69
    POSITIVE LOGITS
    estabelecimento
    0.99
     alun
    0.98
    sylvania
    0.96
    []);
    0.95
    annam
    0.95
     menstruation
    0.94
     submenu
    0.94
    ামান
    0.94
     اخرى
    0.93
     shutterstock
    0.93
    Activations Density 0.764%

    No Known Activations