© 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. 14603
    Prev
    Next
    INDEX
    Explanations

    chorus labels

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

    The neuron fires on the second-person perfect construction “you have” (as in “you have done…”).

    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
    er
    0.95
    spray
    0.95
    nan
    0.94
    tu
    0.91
    r
    0.89
     Info
    0.87
    n
    0.84
    sunday
    0.84
    dream
    0.83
    cez
    0.83
    POSITIVE LOGITS
    ರೀ
    0.84
     seeming
    0.80
     sightings
    0.79
     쿠
    0.79
     crushing
    0.78
     água
    0.78
     recuperação
    0.77
     retorno
    0.77
     Brasília
    0.77
     versões
    0.77
    Activations Density 0.000%

    No Known Activations