© 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. 8643
    Prev
    Next
    INDEX
    Explanations

    immediate relief and strategies

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

    The neuron specializes in spotting bibliographic ISBN number sequences (numbers and hyphens in the 13-digit ISBN format).

    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
    ᒧ
    0.82
    ному
    0.79
    емой
    0.79
    ТР
    0.79
     KEYUP
    0.79
    веде
    0.78
     달리
    0.77
    ennzeichnet
    0.77
    𝚘
    0.77
    orters
    0.77
    POSITIVE LOGITS
    .
    0.90
    ,
    0.79
    men
    0.73
     číslo
    0.71
     były
    0.70
     màn
    0.69
     bajo
    0.67
    lsen
    0.67
     tú
    0.64
     stronę
    0.64
    Activations Density 0.001%

    No Known Activations