© 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. 6734
    Prev
    Next
    INDEX
    Explanations

    string literals

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

    The neuron strongly activates on literal string values (text enclosed in quotes) in code or output, i.e. it detects quoted string tokens.

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Each
    -2.19
    </
    -2.16
    }
    -2.16
     Also
    -2.16
     Both
    -2.09
     It
    -2.05
    The
    -2.03
    They
    -2.02
    Then
    -2.00
     Should
    -1.99
    POSITIVE LOGITS
     accentu
    1.95
    
    1.75
     continúas
    1.72
    を活用
    1.72
    anime
    1.70
     rése
    1.63
     vijf
    1.59
    erm
    1.57
    面色
    1.56
     trzec
    1.55
    Activations Density 0.003%

    No Known Activations