© 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. 64440
    Prev
    Next
    INDEX
    Explanations

    locations and organizations

    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
    Clown
    -0.90
    closures
    -0.90
    ׇ
    -0.88
     mandato
    -0.87
     meninas
    -0.86
     graus
    -0.85
    ῶν
    -0.84
    Gnome
    -0.83
     you
    -0.83
    别人
    -0.83
    POSITIVE LOGITS
     its
    1.27
    ַּ
    1.24
    ֶּ
    1.16
    ִּ
    1.13
    ּוֹ
    1.04
     requested
    1.01
    ְּ
    0.97
    OLIC
    0.97
     request
    0.96
    omato
    0.94
    Activations Density 0.079%

    No Known Activations