© 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. 72173
    Prev
    Next
    INDEX
    Explanations

    "I am" followed by action verbs

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     there
    -1.74
     what
    -1.69
     for
    -1.61
     as
    -1.59
     find
    -1.46
     an
    -1.43
     before
    -1.42
     can
    -1.41
     all
    -1.40
     creating
    -1.38
    POSITIVE LOGITS
    ⅴ
    1.64
     نوز
    1.54
     メニュー
    1.46
     öffnungszeiten
    1.43
     qualités
    1.41
     этих
    1.38
     personnaliser
    1.36
    谖
    1.36
     vrais
    1.36
     possibilités
    1.34
    Activations Density 0.087%

    No Known Activations