© 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. 10325
    Prev
    Next
    INDEX
    Explanations

    quoted text or variable assignment

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

    The neuron fires on forward‐slash tokens (i.e. “/”)—for example parts of URLs or file‐path separators.

    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
    لین
    0.87
    ل
    0.86
    รู้สึก
    0.85
     réussir
    0.79
    ્ષ
    0.79
    ROIT
    0.78
     crackers
    0.77
    华
    0.77
     bhikkhave
    0.76
     médicament
    0.75
    POSITIVE LOGITS
    rom
    0.82
    improve
    0.77
    se
    0.75
    ud
    0.73
    ᅵ
    0.73
     требует
    0.71
    wing
    0.69
    ::
    0.68
    ust
    0.68
    severe
    0.68
    Activations Density 0.001%

    No Known Activations