© 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. 2176
    Prev
    Next
    INDEX
    Explanations

    interested, helpful, given, convenience

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

    This neuron activates on polite, customer‐friendly phrases offering help or guidance (e.g., “for your reference” or “for your convenience”).

    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
     a
    0.58
    らかな
    0.56
     saucer
    0.53
    氏は
    0.53
    }=\
    0.53
    ంటి
    0.52
    ಧಾನ
    0.52
    ప్రదేశ
    0.52
     horrific
    0.50
     प्रकारचे
    0.50
    POSITIVE LOGITS
    ‌.
    1.04
    ."
    1.00
    ។
    0.98
    .‏
    0.95
    .*
    0.94
    .<
    0.94
    .`
    0.93
    .
    0.93
    .??
    0.92
    .。
    0.92
    Activations Density 0.000%

    No Known Activations