© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13836
    Prev
    Next
    INDEX
    Explanations

    citations or numbered lists

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

    The neuron fires on numeric tokens (i.e. standalone numbers).

    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
     herein
    0.79
     $)$.
    0.75
     ];
    0.70
    _;
    0.70
     により
    0.70
    \}.
    0.67
    ].
    0.67
     による
    0.67
     utils
    0.65
     cookieParser
    0.65
    POSITIVE LOGITS
    addEnemy
    0.69
    소년
    0.65
    ithing
    0.63
     WrestleMania
    0.62
    Người
    0.62
     그는
    0.58
    缟
    0.58
    他在
    0.57
     चाहती
    0.56
    人は
    0.56
    Activations Density 0.000%

    No Known Activations