© 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. 10-GEMMASCOPE-RES-131K
    7. 72335
    Prev
    Next
    INDEX
    Explanations

    quoted strings or code literals

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

    The neuron is detecting number‐like tokens (integer or floating‐point literals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -2.02
    </h4>
    -1.98
     liknande
    -1.81
     just
    -1.78
     get
    -1.74
    or
    -1.74
     also
    -1.70
     for
    -1.69
     ungefär
    -1.64
    ay
    -1.63
    POSITIVE LOGITS
     harán
    1.91
     exemplifies
    1.86
    ptăm
    1.80
    GRAFÍA
    1.74
     assistente
    1.73
     escritório
    1.72
    鶲
    1.72
     affirms
    1.70
     })}
    1.68
    祼
    1.68
    Activations Density 0.188%

    No Known Activations