© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7746
    Prev
    Next
    INDEX
    Explanations

    advertise, lives, name, amount, payment

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

    The neuron detects evaluative adjectives—single words that express a quality or opinion (e.g. “advanced,” “free,” “kind,” “whole,” “practical,” “confident,” etc.).

    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
     Kavanaugh
    0.83
    ǁ
    0.81
    PARAMS
    0.78
    ト
    0.78
    𝗖
    0.78
     Kelly
    0.74
    ститут
    0.73
     Fabrizio
    0.72
    ﺕ
    0.72
     ڈھ
    0.71
    POSITIVE LOGITS
    op
    1.03
    omp
    0.81
    usp
    0.80
     manchas
    0.76
     toma
    0.73
     excelente
    0.73
     kui
    0.71
    idl
    0.71
    analytic
    0.71
     elegante
    0.70
    Activations Density 0.001%

    No Known Activations