© 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. 11382
    Prev
    Next
    INDEX
    Explanations

    demonstrate or show

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

    The neuron activates on the verb “show” (and its forms like shows, showed, shown, showing).

    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
    𝗂
    0.98
    <0x80>
    0.95
    িমুখে
    0.88
    0.86
    𝖽
    0.86
     Prediction
    0.86
     GameOver
    0.85
    意味着
    0.84
     cautioned
    0.84
     optimised
    0.84
    POSITIVE LOGITS
    ка
    1.18
    踪
    1.16
    ти
    1.12
     کہ
    1.10
    та
    1.09
     드러
    1.09
     conclusively
    1.05
    ร
    0.98
    跡
    0.96
     gebe
    0.92
    Activations Density 0.478%

    No Known Activations