© 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. 5670
    Prev
    Next
    INDEX
    Explanations

    step by step

    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
    CacheV
    1.23
    <unused1778>
    1.17
    <unused1875>
    1.15
    <unused384>
    1.14
    勎
    1.14
    雬
    1.13
    ၡ
    1.13
    <unused306>
    1.12
    <unused410>
    1.11
    <unused1990>
    1.11
    POSITIVE LOGITS
    ጎ
    0.82
    refer
    0.81
    keywords
    0.78
    un
    0.77
    ্নে
    0.76
    ということは
    0.75
    なんです
    0.75
     (
    0.74
     referring
    0.74
     Beth
    0.74
    Activations Density 0.342%

    No Known Activations