© 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. 11552
    Prev
    Next
    INDEX
    Explanations

    line-by-line explanation

    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
    patan
    1.12
    ুদ
    1.11
    زان
    1.04
    准
    1.03
    куляр
    1.02
    けば
    1.02
     accordingly
    1.01
    \|
    1.01
     آنچه
    1.01
     correspondiente
    1.01
    POSITIVE LOGITS
    tourism
    1.20
     tourism
    1.20
     yoğun
    1.19
    y
    1.12
     phone
    1.09
     Tourism
    1.08
     raw
    1.07
    soup
    1.06
    Tourism
    1.05
     steve
    1.04
    Activations Density 0.000%

    No Known Activations