© 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. 13367
    Prev
    Next
    INDEX
    Explanations

    body hair length

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

    The neuron fires on content words immediately following numeric or measurement cues (e.g. after recipe‐step numbers, quantities, statistics).

    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
    пы
    0.70
    '>{
    0.70
     endpoints
    0.70
     insertions
    0.69
     privile
    0.68
    \{
    0.67
     isos
    0.66
     phys
    0.66
    有害
    0.65
    вы
    0.65
    POSITIVE LOGITS
    uğ
    0.91
    Avec
    0.88
    Hace
    0.87
    ına
    0.82
    İ
    0.82
    alamat
    0.81
     İşte
    0.81
     Doğ
    0.80
    çok
    0.79
    oarece
    0.79
    Activations Density 0.000%

    No Known Activations