© 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. 7146
    Prev
    Next
    INDEX
    Explanations

    color names, code structures

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

    The neuron responds to unusually rare or out-of-vocabulary tokens (it spikes on low-frequency, uncommon words).

    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
    PhotoMode
    0.72
    ونية
    0.67
    ☓
    0.66
    ძლ
    0.65
    yr
    0.64
     skies
    0.63
    Drinks
    0.63
    edin
    0.63
    ר
    0.63
    SOURCES
    0.62
    POSITIVE LOGITS
     cuja
    0.89
    <0xA8>
    0.79
     comprador
    0.78
    enser
    0.77
    ට්
    0.76
     मछ
    0.76
     Ganga
    0.75
    routingHeader
    0.75
    ically
    0.73
    enciar
    0.73
    Activations Density 0.001%

    No Known Activations