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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 75308
    Prev
    Next
    INDEX
    Explanations

    other or another instance

    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
    oquia
    -1.08
    odly
    -1.04
     then
    -1.02
     EVERYTHING
    -1.02
     cómo
    -1.00
    gdala
    -1.00
    了她
    -0.98
     EVERYONE
    -0.97
     when
    -0.96
    äts
    -0.95
    POSITIVE LOGITS
     other
    3.70
    other
    2.42
     других
    2.28
    Other
    2.25
    其他
    2.22
     andere
    2.19
     others
    2.13
     autres
    2.08
     другие
    2.06
     інших
    2.05
    Activations Density 0.056%

    No Known Activations