© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13727
    Prev
    Next
    INDEX
    Explanations

    elliptic curve cryptography

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

    The neuron fires on specialized hyphenated or multi‐part technical terms (e.g. p-adic, K-theory, Elliptic-Surface-Singularities, 20-day SMA).

    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_31_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
    ())));
    0.65
     saa
    0.65
     Installer
    0.64
    ভাস
    0.62
    Installer
    0.60
     öffent
    0.59
     öffentlichen
    0.59
     Universitas
    0.58
    ￩
    0.58
     தேர்
    0.57
    POSITIVE LOGITS
    metrics
    0.72
    points
    0.66
    ................
    0.65
     compliance
    0.63
    ability
    0.62
    scaling
    0.62
    compliance
    0.61
    ################
    0.61
     metrics
    0.59
     parameters
    0.59
    Activations Density 0.001%

    No Known Activations