© 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. 7124
    Prev
    Next
    INDEX
    Explanations

    new words do not exist yet

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

    The neuron fires most strongly on unusually rare or low‐frequency words (i.e. it acts like an “IDF” detector).

    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
     advers
    0.86
     armada
    0.84
    гой
    0.77
    出力
    0.75
    m
    0.75
    mation
    0.75
     geometria
    0.74
    t
    0.74
     estacion
    0.73
     knob
    0.71
    POSITIVE LOGITS
    בית
    0.76
    elmi
    0.71
    کي
    0.70
    खे
    0.69
    Dat
    0.68
    )».
    0.68
    ")}}
    0.68
    qar
    0.68
    *_
    0.67
    एसएल
    0.67
    Activations Density 0.001%

    No Known Activations