© 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. 6641
    Prev
    Next
    INDEX
    Explanations

    shows evidence

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

    The neuron responds to tokens containing numbers—i.e. numeric values, measurements, statistics, or any digit‐based strings.

    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
     軽量
    0.73
     Использу
    0.70
    СФ
    0.68
    Pentru
    0.68
     использоваться
    0.67
     Untuk
    0.67
    Untuk
    0.66
     搭
    0.66
    Subgraph
    0.66
     इन्हे
    0.64
    POSITIVE LOGITS
     reveals
    1.38
    を見ると
    1.38
     confirms
    1.35
     indicates
    1.25
     thấy
    1.23
     clues
    1.20
     confirm
    1.20
     indicate
    1.17
     revealed
    1.16
     보면
    1.16
    Activations Density 1.079%

    No Known Activations