© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6848
    Prev
    Next
    INDEX
    Explanations

    " or "

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

    This neuron responds to numeric expressions (tokens representing numbers, including decimals and 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_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
     কখনও
    0.41
     দুইটি
    0.35
     Jeżeli
    0.35
     কারও
    0.32
    垟
    0.31
    一本
    0.31
     jeżeli
    0.31
     નું
    0.31
    ट
    0.31
     এখনও
    0.30
    POSITIVE LOGITS
    alez
    0.30
    .
    0.30
    insa
    0.28
     --->
    0.28
    rizz
    0.28
    oush
    0.27
    ycz
    0.27
    ావ
    0.27
    afu
    0.27
    ixer
    0.27
    Activations Density 2.674%

    No Known Activations