© 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. 31-GEMMASCOPE-2-RES-16K
    7. 340
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on short alphanumeric ID strings (especially runs of hex‐style digits/letters) that look like cache or URL path identifiers.

    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_31_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
    欹
    0.45
     तीव्रता
    0.42
     महत्त्व
    0.41
    खाव
    0.41
    ዃ
    0.40
    णाच्या
    0.40
    तेक
    0.39
     lowland
    0.39
     मोठ्या
    0.39
    necked
    0.38
    POSITIVE LOGITS
    0.57
    0.52
    //
    0.52
            
    0.51
        
    0.50
     =>
    0.50
    /**
    0.48
    ::
    0.47
     =
    0.47
    0.46
    Activations Density 0.030%

    No Known Activations