© 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. 1685
    Prev
    Next
    INDEX
    Explanations

    times, years, activity

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

    The neuron is essentially a detector for the ampersand character (“&”), as used in ad‐style list or promotional text.

    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
    вання
    0.96
     chiamato
    0.95
    ব
    0.95
    いますが
    0.91
    су
    0.90
    ђу
    0.87
    り
    0.86
    ну
    0.84
    нут
    0.83
    থ
    0.83
    POSITIVE LOGITS
     ♪
    0.76
     OZ
    0.72
     انگ
    0.71
     Damn
    0.70
     ABS
    0.68
     %%
    0.68
     Augusta
    0.66
     greenhouse
    0.65
     archae
    0.65
     AFB
    0.65
    Activations Density 0.007%

    No Known Activations