© 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. 67921
    Prev
    Next
    INDEX
    Explanations

    information categories and links

    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
     maisha
    -1.02
     personaggi
    -0.98
    øren
    -0.98
     sababu
    -0.96
    んでも
    -0.94
    ∶
    -0.94
    kém
    -0.90
    koneksi
    -0.90
     maji
    -0.89
     habari
    -0.89
    POSITIVE LOGITS
     if
    1.27
     more
    1.15
    робнее
    1.05
     of
    1.01
     other
    0.99
     see
    0.98
     or
    0.96
     comparable
    0.94
     here
    0.93
     further
    0.91
    Activations Density 0.039%

    No Known Activations