© 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. 39301
    Prev
    Next
    INDEX
    Explanations

    academic year and sports roles

    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
     but
    -1.12
     krijgen
    -0.99
     to
    -0.98
    тали
    -0.98
     into
    -0.96
     location
    -0.94
     ersten
    -0.94
    //!
    -0.94
     молодо
    -0.93
     tendrá
    -0.93
    POSITIVE LOGITS
     captain
    1.14
    Lundi
    1.11
     extenso
    1.06
     остальных
    1.06
    めんな
    1.05
    karena
    1.02
     desnuda
    1.02
     bambou
    1.01
     войне
    0.99
     Seul
    0.99
    Activations Density 0.007%

    No Known Activations