© 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. 93320
    Prev
    Next
    INDEX
    Explanations

    GUI version, input voltage, nerve terminals, progressive disease

    np_acts-logits-general · gemini-2.5-flash-lite

    technical or specialized terms within academic, scientific, or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    なのでしょう
    -1.18
     terminé
    -1.12
     it
    -1.12
     pudesse
    -1.11
    なんだろう
    -1.09
    报表
    -1.03
     JMenuItem
    -1.02
    opies
    -1.02
     ActionListener
    -1.00
    haviours
    -1.00
    POSITIVE LOGITS
    /
    1.23
     florales
    1.16
    nguyen
    1.13
     vitales
    1.13
     kartą
    1.09
     casado
    1.05
     tenacious
    1.00
     hvem
    1.00
    ólogos
    0.99
     dieną
    0.99
    Activations Density 0.039%

    No Known Activations