© 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. 13630
    Prev
    Next
    INDEX
    Explanations

    terminal or command prompt

    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
    )|$(
    1.65
    se
    1.54
    ↵
    1.53
    ken
    1.50
    नायक
    1.49
    ".
    1.48
    "
    1.45
     Nok
    1.43
    gr
    1.42
     d
    1.42
    POSITIVE LOGITS
    ’’’’
    2.57
    sthresh
    2.37
    লির
    2.35
    âtres
    2.33
    ulé
    2.32
    ील
    2.31
    пикир
    2.30
    FileAlignment
    2.29
    ELLOW
    2.29
    iax
    2.28
    Activations Density 0.198%

    No Known Activations