© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8511
    Prev
    Next
    INDEX
    Explanations

    be is to be

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

    This neuron fires on numeric tokens and quantitative details—e.g. prices, ratings, counts, distances—highlighting when the text mentions numbers and measurable values.

    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
    charg
    0.58
    ziehungen
    0.55
    charger
    0.55
    投資
    0.53
    ઠ
    0.52
     vorg
    0.52
    absch
    0.52
    Charg
    0.49
    investissement
    0.49
    روس
    0.49
    POSITIVE LOGITS
     Easter
    0.59
    体の
    0.58
     Petrov
    0.58
     medit
    0.57
    🧩
    0.55
    大好き
    0.55
     Мне
    0.53
     Cea
    0.53
     Lik
    0.52
     Valentin
    0.50
    Activations Density 0.034%

    No Known Activations