© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2602
    Prev
    Next
    INDEX
    Explanations

    helpful phrase completion

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

    The neuron selectively activates on words evaluating service and staff—e.g. terms referring to owners, service quality, efficiency, friendliness, or rudeness.

    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_31_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
    …).
    0.72
    ...).
    0.71
    ).]
    0.70
    <u>
    0.64
    <sup>
    0.64
    ?).
    0.63
    ण्डी
    0.63
    BTW
    0.63
    too
    0.62
     (
    0.61
    POSITIVE LOGITS
     ，
    1.10
     ،
    0.98
     ৷
    0.98
     ,
    0.97
     ၊
    0.96
     、
    0.95
     ,,
    0.89
     ,'
    0.88
     ,"
    0.84
    ､
    0.82
    Activations Density 0.132%

    No Known Activations