© 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. 5387
    Prev
    Next
    INDEX
    Explanations

    answer in one word

    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
     бри
    1.00
     раза
    0.96
     нам
    0.94
     финан
    0.93
     tudo
    0.92
    僕
    0.89
     (
    0.89
    ああ
    0.87
    бки
    0.86
     все
    0.86
    POSITIVE LOGITS
     elementary
    1.26
     archaeological
    1.24
     subcluster
    1.20
     sixteenth
    1.20
     predetermined
    1.19
    otopic
    1.19
     probabilistic
    1.19
     propagation
    1.19
     elementName
    1.17
    <unused1948>
    1.17
    Activations Density 0.014%

    No Known Activations