© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64253
    Prev
    Next
    INDEX
    Explanations

    code documentation with multilingual terms

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

    The neuron fires on the end‐of‐comment delimiter “*/,” marking the close of a block or doc comment.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    <td>
    -1.98
    providedIn
    -1.80
     étui
    -1.77
    
    -1.70
     kalori
    -1.68
     kupa
    -1.66
    ции
    -1.66
    逦
    -1.65
    geç
    -1.63
    ция
    -1.61
    POSITIVE LOGITS
    會有
    1.84
    u
    1.78
     fremden
    1.70
    何回
    1.63
     incontr
    1.60
     offiziellen
    1.60
     avesse
    1.59
     africains
    1.59
    頃の
    1.56
    為に
    1.52
    Activations Density 0.012%

    No Known Activations