© 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. 64276
    Prev
    Next
    INDEX
    Explanations

    required fields or items

    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
     or
    -1.24
     chose
    -1.22
     two
    -1.13
     but
    -1.12
     choose
    -1.10
     дуже
    -1.09
     since
    -1.09
     using
    -1.09
     because
    -1.08
    illiard
    -1.07
    POSITIVE LOGITS
     required
    1.45
    required
    1.30
    包括
    1.28
     necessary
    1.27
    elements
    1.16
     requirement
    1.16
     éléments
    1.15
     crucial
    1.14
     mandatory
    1.13
     gerekli
    1.12
    Activations Density 0.055%

    No Known Activations