© 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. 7-GEMMASCOPE-2-RES-16K
    7. 11117
    Prev
    Next
    INDEX
    Explanations

    division and fractions

    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_7_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
    ᾷ
    2.62
    Ñ
    2.61
    மிருந்து
    2.55
    ꯤ
    2.45
    ρ
    2.41
    ниш
    2.40
    ታ
    2.38
    ம்
    2.37
    囗
    2.35
    που
    2.34
    POSITIVE LOGITS
    骼
    2.69
    LaunchScheme
    2.62
    tyn
    2.56
    髅
    2.48
    izumab
    2.46
    髏
    2.39
    epan
    2.35
    mares
    2.30
     komplet
    2.29
     desn
    2.28
    Activations Density 0.026%

    No Known Activations