© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15795
    Prev
    Next
    INDEX
    Explanations

    specific

    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
    اعر
    2.12
    𝐒
    2.11
    ιουργ
    2.08
    e
    2.08
    honia
    1.97
    osaur
    1.97
    initro
    1.96
    eaa
    1.95
    াভাব
    1.95
    oč
    1.95
    POSITIVE LOGITS
     ích
    1.69
    conven
    1.67
     bús
    1.64
     nec
    1.64
    時刻
    1.62
    accessible
    1.59
    isms
    1.58
    𝘇
    1.55
    fulness
    1.54
    স্থ
    1.54
    Activations Density 0.221%

    No Known Activations