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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12310
    Prev
    Next
    INDEX
    Explanations

    C# using System

    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
     kupić
    -1.45
    werkers
    -1.32
     creó
    -1.28
     envía
    -1.27
    LEVANT
    -1.25
    倹
    -1.22
    zumaki
    -1.22
    création
    -1.21
     військо
    -1.19
     sirvió
    -1.18
    POSITIVE LOGITS
    .
    1.13
    <strong>
    1.09
    !
    1.02
    ↵↵
    0.98
    к
    0.96
    It
    0.95
    \
    0.95
    ，
    0.95
    0.92
    ti
    0.90
    Activations Density 0.006%
    No Known Activations