© 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. 10277
    Prev
    Next
    INDEX
    Explanations

    onomatopoeia and sound effects

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

    This neuron fires on informal praise using “rock”/“rocks” (e.g. “this rocks,” “they rock it out”) to signal enthusiastic endorsement.

    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
    ρ
    0.59
    ן
    0.59
    되며
    0.58
    ท
    0.56
    ת
    0.55
    ইতি
    0.55
    ד
    0.55
     mimic
    0.54
    parallax
    0.54
    कून
    0.54
    POSITIVE LOGITS
     concepts
    0.65
     regarding
    0.58
     (=
    0.57
     💪
    0.57
     pragmatic
    0.55
     judgments
    0.54
     RSA
    0.54
     👌
    0.54
     ✨
    0.53
     cristiano
    0.53
    Activations Density 0.000%

    No Known Activations