© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 11976
    Prev
    Next
    INDEX
    Explanations

    analysis, Chart, website, Bureau, roller, form, announced

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

    The neuron strongly activates on capitalized terms and multiword titles or headings (e.g. guide names, section headers, proper‐noun phrases).

    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
    ・・
    0.75
    '-
    0.75
    '&
    0.69
    ''
    0.69
    \'
    0.69
    Etat
    0.69
    ......
    0.68
    !!!
    0.68
    .......
    0.67
    ............
    0.67
    POSITIVE LOGITS
     HERE
    1.44
    <u>
    1.33
     ,
    1.30
     .)
    1.27
     ).
    1.23
     )।
    1.20
     Архивная
    1.15
     ),
    1.14
     ,
    1.13
     。
    1.09
    Activations Density 0.540%

    No Known Activations