© 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. 7184
    Prev
    Next
    INDEX
    Explanations

    2 and years

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

    The neuron never activates on any input—it’s effectively dead (doesn’t detect any pattern).

    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
    September
    0.79
    February
    0.75
    January
    0.72
     February
    0.68
    October
    0.67
    November
    0.67
    사
    0.65
    ㅈ
    0.61
    Archive
    0.61
     ноябре
    0.61
    POSITIVE LOGITS
     blissful
    0.70
     idiopathic
    0.65
     યોગ્ય
    0.64
     dissip
    0.64
     intrusions
    0.63
     exorbit
    0.62
     tantrums
    0.62
     biota
    0.62
     agglomer
    0.61
     fasteners
    0.61
    Activations Density 0.022%

    No Known Activations