© 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. 1901
    Prev
    Next
    INDEX
    Explanations

    four/five/seven/ten pairs

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

    The neuron fires on numeric expressions (digits and multi‐digit numbers) in the 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
     Kedua
    0.70
    两者
    0.68
     두
    0.58
     kedua
    0.57
    สอง
    0.57
     обоих
    0.57
    어를
    0.56
    が多く
    0.56
    서
    0.56
     begge
    0.55
    POSITIVE LOGITS
    teenth
    0.75
    pence
    0.75
    деся
    0.72
     eight
    0.65
    ieth
    0.65
     townships
    0.64
     మంది
    0.63
    మంది
    0.63
     five
    0.62
    eight
    0.62
    Activations Density 0.000%

    No Known Activations