© 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. 8314
    Prev
    Next
    INDEX
    Explanations

    academic citation

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

    The neuron is detecting the initial 0xE2 byte of a multi‐byte UTF-8 sequence (e.g. the start of an em-dash or similar punctuation).

    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
     Physiological
    0.57
     Practices
    0.56
     BVHTree
    0.56
     }
    0.55
    $}
    0.55
    AndroidResource
    0.54
     Soils
    0.54
    artoum
    0.54
    yld
    0.53
     Quantification
    0.53
    POSITIVE LOGITS
     choses
    0.59
     firefighters
    0.59
     offrir
    0.57
     continente
    0.57
     participa
    0.57
     conna
    0.57
    比起
    0.57
     declarar
    0.57
     seaw
    0.56
     ´
    0.56
    Activations Density 0.000%

    No Known Activations