© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 981
    Prev
    Next
    INDEX
    Explanations

    file extensions

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is sensitive to sequences of digits (often including dots) representing numeric codes or decimal numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     infuse
    0.65
     murm
    0.61
     চিন্ত
    0.61
     narrowband
    0.61
    .
    0.58
     encompass
    0.58
     retribution
    0.58
     adolescence
    0.57
     equate
    0.57
     traduce
    0.56
    POSITIVE LOGITS
    jpg
    1.56
    docx
    1.27
    aspx
    1.26
    png
    1.25
    pdf
    1.25
    exe
    1.24
    ᐟ
    1.24
    php
    1.23
    xlsx
    1.20
    indd
    1.18
    Activations Density 0.755%

    No Known Activations