© 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. 10154
    Prev
    Next
    INDEX
    Explanations

    requesting assistance or information

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

    The neuron fires on occurrences of the verb “help” (and its close morphological variants like “helped”).

    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
    Д
    1.30
     Jenis
    1.27
    1.23
    I
    1.22
    Для
    1.16
    轳
    1.13
    岖
    1.13
    JECT
    1.12
    нд
    1.11
    sax
    1.11
    POSITIVE LOGITS
     đỡ
    1.47
     ích
    1.42
     defray
    1.30
    មាន
    1.20
     ويكيپيديا
    1.14
    ول
    1.13
    ا
    1.13
    ం
    1.10
    о
    1.09
    ून
    1.05
    Activations Density 0.098%

    No Known Activations