© 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. 7739
    Prev
    Next
    INDEX
    Explanations

    receiving input or feedback

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

    The neuron activates on words and phrases expressing support, help, or assistance.

    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
    在于
    1.00
    ש
    0.95
     successes
    0.93
    Hej
    0.92
    心思
    0.92
    المل
    0.90
    不去
    0.89
    etar
    0.87
     것이
    0.87
     fundraisers
    0.85
    POSITIVE LOGITS
     receber
    1.17
     RECEIVED
    1.16
     받을
    1.12
     dari
    1.09
     ricevuto
    1.09
     SUPPORT
    1.08
    р
    1.06
     oleh
    1.05
    を受ける
    1.05
     sostegno
    1.05
    Activations Density 1.899%

    No Known Activations