© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9514
    Prev
    Next
    INDEX
    Explanations

    variations and options

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

    The neuron fires on words that label site or show “features” or content sections—e.g. menu‐style headings like “appearances,” “features,” “topic,” “experiments,” “demonstrations,” “charts,” “backlink,” and similar structural labels.

    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
     grotesque
    0.52
     humane
    0.49
     prestar
    0.48
     caspase
    0.46
     hemorrhagic
    0.46
     malignant
    0.46
     credence
    0.46
     נ
    0.46
     laughable
    0.46
     cytotoxic
    0.45
    POSITIVE LOGITS
     With
    0.52
     with
    0.51
    with
    0.49
     But
    0.49
     While
    0.48
    ással
    0.46
    ുകളും
    0.46
    éseket
    0.45
     Here
    0.45
    中心
    0.45
    Activations Density 0.551%

    No Known Activations