© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6177
    Prev
    Next
    INDEX
    Explanations

    **Python code structure and keywords**

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

    The neuron responds to calls‐to‐action directing the reader to visit or click a web link (e.g. “go to web site,” “click the following webpage”).

    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_24_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
    тись
    0.59
    calories
    0.54
    тири
    0.52
    বুব
    0.52
    restaurants
    0.52
    вшись
    0.52
    ailure
    0.51
    casino
    0.51
    izacin
    0.51
     বিপর
    0.50
    POSITIVE LOGITS
     Ā
    0.51
     Peirce
    0.50
     adduced
    0.49
     Ж
    0.48
     Ș
    0.47
     Ё
    0.47
    :\
    0.46
     Förder
    0.46
     McInt
    0.46
     Materialien
    0.45
    Activations Density 0.003%

    No Known Activations