© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6087
    Prev
    Next
    INDEX
    Explanations

    based, like, inspired

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

    This neuron detects tokens that end with a hyphen, i.e. the first parts of hyphenated words.

    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
    ・・・。
    0.47
    ≲
    0.45
    PERTY
    0.42
     \%)$.
    0.42
    ventions
    0.41
     تھی۔
    0.41
    UREG
    0.41
    -]
    0.40
     التقل
    0.40
    ქვენ
    0.40
    POSITIVE LOGITS
    based
    0.46
     plaza
    0.44
    by
    0.43
     hearted
    0.43
    like
    0.41
    backed
    0.40
     category
    0.39
     By
    0.39
     risked
    0.38
    fueled
    0.38
    Activations Density 0.044%

    No Known Activations