© 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. 13821
    Prev
    Next
    INDEX
    Explanations

    URLs and DOIs in academic papers

    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
    意的
    1.78
    añ
    1.78
    laş
    1.76
    𝒐
    1.73
    加坡
    1.73
    ும்
    1.70
    gloss
    1.65
    oit
    1.63
    しい
    1.59
    𝒆
    1.57
    POSITIVE LOGITS
    फत
    1.97
    Iddict
    1.86
    肺炎
    1.83
    ஜ்மஹால்
    1.73
    ซ์
    1.73
    ﺪ
    1.71
    DomainMask
    1.70
    {#
    1.67
    Codigo
    1.66
    NameValuePair
    1.64
    Activations Density 0.049%

    No Known Activations