© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9332
    Prev
    Next
    INDEX
    Explanations

    after B, tell, assertion

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

    The neuron fires on verbs that describe concrete actions or steps in a process (e.g. develop, test, share, proceed, contain, optimize).

    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
    𝐥
    0.84
    ग्ध
    0.84
    <unused1728>
    0.83
    䬲
    0.82
    ल्पन
    0.81
    ృద్ధి
    0.79
    িয়াই
    0.79
    訕
    0.79
     परेशानी
    0.77
    䡈
    0.77
    POSITIVE LOGITS
    =
    1.03
     (=
    0.99
    '
    0.97
    .
    0.94
    !
    0.94
    :
    0.91
     =
    0.90
     เพื่อ
    0.89
    </a>
    0.89
    -
    0.89
    Activations Density 13.423%

    No Known Activations