© 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. 4645
    Prev
    Next
    INDEX
    Explanations

    becoming

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

    The neuron flags statements of apology or disclaimer—phrases where someone denies wrongdoing or accepts accountability (e.g. “racism was never his intention,” “takes full accountability”).

    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
    !
    0.66
    /
    0.66
    ?
    0.64
    !!
    0.64
    .
    0.63
     r
    0.61
     y
    0.61
    /).
    0.60
    ?).
    0.60
    ic
    0.59
    POSITIVE LOGITS
     “[
    1.52
     "[
    1.49
     "...
    1.46
     “…
    1.44
     “‘
    1.42
     “(
    1.31
     "'
    1.28
     "..
    1.27
     "(
    1.26
    “[
    1.25
    Activations Density 0.430%

    No Known Activations