© 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. 3537
    Prev
    Next
    INDEX
    Explanations

    this/these

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

    The neuron specifically detects numeric measurements or statistics—particularly decimal‐point values used for things like ratings, scores, ranks, or other quantitative metrics.

    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
    NUM
    0.77
    Trades
    0.74
    ंड
    0.70
    forderung
    0.69
    Numer
    0.68
    ον
    0.68
    視野
    0.68
    Ĕ
    0.68
    وْ
    0.67
    城市的
    0.67
    POSITIVE LOGITS
     this
    0.91
     podataka
    0.79
     denna
    0.72
     ilk
    0.71
     dentées
    0.71
     questo
    0.70
     acest
    0.70
    this
    0.70
     هذا
    0.68
     questa
    0.68
    Activations Density 0.008%

    No Known Activations