© 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. 31-GEMMASCOPE-2-RES-16K
    4. 11034
    Prev
    Next
    INDEX
    Explanations

    API response code

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

    The neuron flags API- or SDK-style documentation lines that describe reading, discarding, or returning an HTTP response body (e.g. “readJson Reads the whole response body and tries to parse it as JSON”).

    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
    လမ်း
    0.59
    脐
    0.57
    Kob
    0.57
    GetValue
    0.55
    Couple
    0.55
    Matched
    0.55
     Lafayette
    0.54
    programm
    0.54
    湊
    0.53
    agli
    0.53
    POSITIVE LOGITS
     json
    0.61
     resposta
    0.58
     áo
    0.58
    json
    0.57
     Response
    0.57
    面白い
    0.57
     response
    0.57
    剐
    0.56
     réponse
    0.55
     protección
    0.55
    Activations Density 0.003%

    No Known Activations