© 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. 114041
    Prev
    Next
    INDEX
    Explanations

    JSON key-value pairs

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

    the opening bracket in a list assignment or definition statement in code (typically after an equals sign).

    oai_token-act-pair · claude-4-5-sonnet
    Triggered by @bfgcn7frf5
    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
    v
    -1.55
     også
    -1.55
     Different
    -1.55
     also
    -1.52
    有
    -1.45
     causes
    -1.41
     也
    -1.41
     faced
    -1.39
    em
    -1.37
    if
    -1.37
    POSITIVE LOGITS
    鸶
    1.66
    itisation
    1.54
    ſſen
    1.48
    melse
    1.44
     huit
    1.43
    蔼
    1.43
    我们会
    1.40
     tega
    1.40
    credited
    1.39
     akun
    1.36
    Activations Density 0.003%

    No Known Activations