© 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. 10262
    Prev
    Next
    INDEX
    Explanations

    spoken text

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

    The neuron is highly activated by infrequent, uncommon whole-word tokens (i.e. rare or low-frequency 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
    ný
    0.95
    õe
    0.91
    ěla
    0.91
    ši
    0.90
     Дэ
    0.89
     Ainda
    0.89
     wê
    0.88
    i
    0.87
    oría
    0.86
    uat
    0.86
    POSITIVE LOGITS
     anteced
    0.75
    وار
    0.70
    هم
    0.70
     uniqueness
    0.68
     situational
    0.67
    யூ
    0.67
    نس
    0.66
     unique
    0.66
    ومات
    0.64
     annotation
    0.64
    Activations Density 0.000%

    No Known Activations