© 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. 5670
    Prev
    Next
    INDEX
    Explanations

    share in comments

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

    This neuron detects call-to-action phrases soliciting reader feedback in the comments (e.g. “Let us know in the comments,” “Tell us in the comments,” “Share … in comments”).

    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
     হচ্ছিল
    0.65
     খাদ
    0.65
    omata
    0.64
     оказалась
    0.61
     phối
    0.61
    zka
    0.61
    oram
    0.59
    astung
    0.59
    oshin
    0.59
    .}}
    0.59
    POSITIVE LOGITS
    いろんな
    0.87
    いろいろ
    0.86
    考えると
    0.76
    ぐらい
    0.72
     bambino
    0.68
    一部分
    0.67
    tomorrow
    0.67
    𝕝
    0.66
    например
    0.66
    sentiment
    0.66
    Activations Density 0.002%

    No Known Activations