© 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. 830
    Prev
    Next
    INDEX
    Explanations

    references [number]

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

    The neuron flags tokens that serve as footnote or citation markers (e.g. “fn,” superscript letters/numbers), i.e. inline reference markers.

    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
    ourcen
    0.50
    ͹
    0.49
     oublier
    0.48
     coches
    0.46
     proveedores
    0.44
    aurants
    0.44
     fonbet
    0.44
    
    0.43
     conna
    0.42
     बालकनियां
    0.42
    POSITIVE LOGITS
     Brewer
    0.38
     White
    0.35
    ת
    0.35
     Herm
    0.34
     they
    0.34
     hide
    0.34
    性
    0.34
     Dye
    0.34
     a
    0.34
     repeatedly
    0.34
    Activations Density 0.001%

    No Known Activations