© 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. 1674
    Prev
    Next
    INDEX
    Explanations

    How things work

    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
     將
    0.90
    ikul
    0.90
     помогут
    0.89
    हिमा
    0.86
    拿出
    0.86
    ပြ
    0.85
     menyaksikan
    0.85
    <0xAA>
    0.85
    賢
    0.84
    wiata
    0.83
    POSITIVE LOGITS
    なので
    1.45
    ですから
    1.42
    인데
    1.39
     поэтому
    1.36
    だから
    1.33
    ですので
    1.30
     لذا
    1.27
    이니까
    1.27
     rather
    1.25
     portanto
    1.24
    Activations Density 1.063%

    No Known Activations