© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 26441
    Prev
    Next
    INDEX
    Explanations

    academic research and findings

    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
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.26
     orígenes
    -1.23
    
    -1.20
    ieron
    -1.17
    jobb
    -1.16
    gör
    -1.16
    bilden
    -1.14
     *}$
    -1.12
     וכן
    -1.11
    lsz
    -1.10
    POSITIVE LOGITS
     is
    1.67
     this
    1.53
     of
    1.20
     here
    1.16
     này
    1.15
    นี้
    1.13
     Ornaments
    1.12
     этом
    1.10
     includes
    1.09
    まと
    1.09
    Activations Density 0.131%

    No Known Activations