© 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. 4995
    Prev
    Next
    INDEX
    Explanations

    SQL code closing syntax

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

    The neuron fires on standalone list‐item or diff markers (e.g. lines beginning with “*” or “+”), i.e. on tokens that mark bullets or added lines.

    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
     S
    0.89
     Toms
    0.85
     J
    0.82
     g
    0.78
     O
    0.78
     n
    0.77
     K
    0.77
     M
    0.76
     yc
    0.76
     川
    0.75
    POSITIVE LOGITS
    .
    0.80
    रविवार
    0.80
    )
    0.79
    })
    0.76
     poderia
    0.75
    Однако
    0.75
    },$
    0.75
    कृपया
    0.74
    ”，
    0.74
    ”،
    0.73
    Activations Density 0.010%

    No Known Activations