© 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. 9910
    Prev
    Next
    INDEX
    Explanations

    encoding and decoding

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

    The neuron activates strongly on technical computing and programming terms (like “coding,” “programming,” “code,” “function,” etc.).

    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
     регистра
    0.62
    बूझ
    0.62
     реєстра
    0.61
    ኛ
    0.59
    ையாக
    0.59
     риска
    0.59
     Archivlink
    0.58
     साजिश
    0.57
     регистрации
    0.57
     hInstance
    0.56
    POSITIVE LOGITS
     MPP
    0.56
    عليه
    0.56
    <em>
    0.53
    </strong>
    0.53
     utf
    0.53
    seen
    0.53
     spotted
    0.53
     verd
    0.50
     namens
    0.50
     Brief
    0.50
    Activations Density 0.000%

    No Known Activations