© 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. 8160
    Prev
    Next
    INDEX
    Explanations

    worth the effort, worth it

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

    The neuron strongly activates on the word “worth” (i.e. when a statement expresses that something “is worth” some amount).

    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
    ли
    1.20
    นี
    1.09
    ר
    1.02
    不由
    0.97
    นั้น
    0.96
    る
    0.96
    มัน
    0.96
    ˋ
    0.95
    ນີ້
    0.93
    मोह
    0.92
    POSITIVE LOGITS
    WORTH
    1.03
    HAL
    0.97
    iz
    0.93
    ită
    0.93
    ic
    0.93
    name
    0.90
    worth
    0.88
    منت
    0.88
    σης
    0.88
    तरंज
    0.88
    Activations Density 0.029%

    No Known Activations