© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12971
    Prev
    Next
    INDEX
    Explanations

    clever, playful response

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

    The neuron flags tokens containing digits (i.e. numerical strings such as dates, codes, measurements, etc.)

    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
    ل
    0.89
    ре
    0.85
     मुझे
    0.84
     animating
    0.81
    ร
    0.79
     recommending
    0.77
     accumulating
    0.76
    ր
    0.76
    то
    0.75
     brightly
    0.75
    POSITIVE LOGITS
     centra
    0.77
     carénés
    0.76
    ées
    0.73
    aires
    0.72
    个月
    0.72
     lahat
    0.72
     ঘাট
    0.71
    asure
    0.70
    asses
    0.70
    ression
    0.69
    Activations Density 0.000%

    No Known Activations