© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 942
    Prev
    Next
    INDEX
    Explanations

    javascript module imports

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

    This neuron detects informal greeting salutations at the start of a message (e.g. “Hi there,” “Hello guys,” “Hi everyone”).

    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
    ຕ້ອງ
    0.44
     berücksichtigt
    0.42
    тное
    0.42
    ੳ
    0.41
    ຈັດ
    0.41
    ूरती
    0.40
    шивания
    0.40
    ňuje
    0.39
    ция
    0.39
    ເຊ
    0.39
    POSITIVE LOGITS
     ,
    0.59
     ,
    0.57
     và
    0.53
     and
    0.49
    d
    0.48
    $,
    0.47
     এবং
    0.46
     、
    0.45
     και
    0.44
     మరియు
    0.43
    Activations Density 0.001%

    No Known Activations