© 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. 40380
    Prev
    Next
    INDEX
    Explanations

    rosales. aralen. policy. summary

    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
     lots
    -1.07
    臟
    -1.00
    しましたが
    -0.97
    كتور
    -0.90
     large
    -0.89
     our
    -0.89
     號
    -0.89
     absent
    -0.88
     various
    -0.88
     most
    -0.88
    POSITIVE LOGITS
    Literat
    1.16
    Nguyên
    1.10
    zehnten
    1.06
     DER
    1.00
    atiker
    0.99
     天然
    0.97
    equila
    0.96
     violen
    0.95
    cticide
    0.94
    GRAP
    0.93
    Activations Density 0.109%

    No Known Activations