© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5287
    Prev
    Next
    INDEX
    Explanations

    sounds

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

    This neuron fires on first‐person, subjective reactions (e.g. “I…”, “sorry…”, “hope…”)—i.e. personal commentary or empathetic responses.

    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
     please
    0.80
     Please
    0.71
     PLEASE
    0.70
     YES
    0.68
    please
    0.64
     yes
    0.64
    请
    0.62
    請
    0.59
     grazie
    0.59
    YES
    0.58
    POSITIVE LOGITS
    Sounds
    1.37
     Sounds
    1.31
    sounds
    1.22
     sounds
    1.21
     sonidos
    0.94
    Interesting
    0.89
     intéressant
    0.88
     suena
    0.87
    Hmmm
    0.87
     interessant
    0.85
    Activations Density 0.170%

    No Known Activations