© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13103
    Prev
    Next
    INDEX
    Explanations

    complex descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_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
    ❦
    0.68
    をもって
    0.57
     เท่า
    0.56
     isomer
    0.56
    Temporal
    0.55
    rú
    0.55
    ❧
    0.54
    ⸜
    0.54
    ➽
    0.53
     있어서
    0.52
    POSITIVE LOGITS
    ंद्रा
    0.66
    cattle
    0.63
     buggy
    0.63
     disruptive
    0.63
     cheques
    0.63
     nerdy
    0.61
     crude
    0.61
     fetchData
    0.61
     মহারাজ
    0.59
     rebus
    0.58
    Activations Density 0.000%

    No Known Activations