© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12342
    Prev
    Next
    INDEX
    Explanations

    multi-language words

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

    The neuron detects technical descriptions of filling or injecting liquid resin uniformly into gaps during a manufacturing process.

    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
    વાનું
    0.89
     करण्याची
    0.77
     বিষয়ক
    0.70
     comité
    0.68
     करण्याचे
    0.68
    がいる
    0.65
     Está
    0.63
     solicitation
    0.63
     concetto
    0.62
     distingue
    0.62
    POSITIVE LOGITS
    쯤
    1.18
    までに
    1.14
    時点で
    1.14
    부터
    1.13
    에도
    1.11
    以來
    1.08
    에는
    1.05
    까지
    1.05
    以来
    1.00
    以内に
    0.99
    Activations Density 0.022%

    No Known Activations