© 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. 11701
    Prev
    Next
    INDEX
    Explanations

    get really interesting

    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
     andRow
    1.70
    ￢
    1.67
    Aslamualaikum
    1.64
     rbuf
    1.62
    த்ரே
    1.61
    𐰀
    1.60
     பள்ளத்தா
    1.56
     getHeight
    1.55
    "+"|".
    1.54
     옆
    1.54
    POSITIVE LOGITS
    <i>
    0.87
    <em>
    0.87
    <strong>
    0.85
    <sup>
    0.80
    <b>
    0.80
     no
    0.79
    icamente
    0.75
    <start_of_image>
    0.73
     deveria
    0.71
     somewhat
    0.66
    Activations Density 0.036%

    No Known Activations