© 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. 2933
    Prev
    Next
    INDEX
    Explanations

    closing code delimiters

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

    This neuron spotlights source‐code commentary or log/output lines (i.e. lines beginning with comment markers like //, #, or echo outputs).

    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
    ↵
    0.52
    #!/
    0.51
     op
    0.51
    <
    0.49
     alph
    0.49
    DEFG
    0.49
     gen
    0.49
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.48
     vi
    0.48
     com
    0.47
    POSITIVE LOGITS
     recordó
    0.72
     ],"
    0.68
     }];
    0.66
    \"]
    0.65
     时尚
    0.64
    abbanti
    0.64
    िज़
    0.63
    וֹ
    0.63
     LikeLike
    0.63
     selectTable
    0.63
    Activations Density 0.004%

    No Known Activations