© 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. 32805
    Prev
    Next
    INDEX
    Explanations

    string concatenation operators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    This
    -1.83
    It
    -1.77
    Other
    -1.75
    providedIn
    -1.72
    Unlike
    -1.72
     It
    -1.66
    These
    -1.64
    Only
    -1.64
     Unlike
    -1.62
    Not
    -1.60
    POSITIVE LOGITS
    犼
    1.60
    iog
    1.57
    rofl
    1.54
    “
    1.53
    たまた
    1.43
    DAMN
    1.41
     "
    1.40
    が多い
    1.38
    weightedMode
    1.36
     kleinere
    1.33
    Activations Density 0.002%

    No Known Activations