© 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. 8106
    Prev
    Next
    INDEX
    Explanations

    sounds and noises

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

    The neuron fires on words describing sounds or onomatopoeic noise—i.e. auditory descriptions.

    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
     eyep
    0.59
    脸
    0.57
     దర్శ
    0.55
    一眼
    0.55
    睞
    0.54
     얼굴
    0.53
    臉
    0.53
    対策
    0.49
     cancerous
    0.49
     मिर्च
    0.49
    POSITIVE LOGITS
     звук
    2.63
     sounds
    2.52
     sound
    2.42
     sonido
    2.38
     noises
    2.34
     sonidos
    2.31
    sounds
    2.30
     zvuk
    2.30
     зву
    2.28
    sound
    2.25
    Activations Density 0.594%

    No Known Activations