© 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. 5610
    Prev
    Next
    INDEX
    Explanations

    code get method calls

    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
    ी
    2.76
    ybės
    2.57
    ია
    2.20
     runde
    2.17
    𝘬
    2.12
    jších
    2.11
    ი
    2.08
    odore
    2.08
    শালী
    2.08
    ानि
    2.06
    POSITIVE LOGITS
    XK
    2.43
    வாச
    2.27
    臾
    2.21
    Enumer
    2.12
    Vos
    2.12
    طع
    2.08
    CONDS
    2.08
    rue
    2.06
     jell
    2.05
    אות
    2.03
    Activations Density 0.358%

    No Known Activations