© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 14399
    Prev
    Next
    INDEX
    Explanations

    ratings and reviews

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

    The neuron fires on the numeric parts of star‐rating metadata (e.g. the “X out of Y based on Z reviews” ratings).

    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
    プレート
    0.65
    ں
    0.64
    可愛い
    0.63
    ずつ
    0.62
    room
    0.59
    ポーター
    0.59
     bohater
    0.59
    }+...
    0.59
    า
    0.59
    ەش
    0.59
    POSITIVE LOGITS
    consumers
    0.66
     பல்வேறு
    0.64
    大多数
    0.63
     popularized
    0.63
     اقدامات
    0.62
    梼
    0.62
     सरकारने
    0.62
    Ყ
    0.61
    某些
    0.61
    Wikipedia
    0.61
    Activations Density 0.011%

    No Known Activations