© 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. 10499
    Prev
    Next
    INDEX
    Explanations

    entity extraction and recognition

    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
    愎
    2.55
    asey
    2.50
    ancellation
    2.49
    Hochspringen
    2.47
    ..</
    2.41
    გორ
    2.36
    یثیت
    2.33
    дом
    2.31
    ưa
    2.30
    "<<
    2.29
    POSITIVE LOGITS
    рях
    2.66
     pene
    2.59
    ia
    2.45
    seign
    2.44
     ContentView
    2.43
     mongoose
    2.36
    znam
    2.36
    नाइटेड
    2.36
    useState
    2.31
     lạc
    2.30
    Activations Density 0.007%

    No Known Activations