© 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. 11089
    Prev
    Next
    INDEX
    Explanations

    Final Answer: $\boxed{...}$

    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
    [,
    1.23
    ombies
    1.21
    》（
    1.21
    调度
    1.17
    boleh
    1.17
     ਕਰੋ
    1.14
     peluang
    1.14
    》《
    1.12
     jabatan
    1.12
    َق
    1.11
    POSITIVE LOGITS
     ancora
    0.95
     thank
    0.92
     THANK
    0.90
    <start_of_image>
    0.90
     теперь
    0.89
    더라구요
    0.88
     właśnie
    0.87
     Rope
    0.87
     выход
    0.86
    adiene
    0.86
    Activations Density 0.085%

    No Known Activations