© 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. 11375
    Prev
    Next
    INDEX
    Explanations

    if and elif statements

    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
     exhibición
    -1.02
    到底
    -1.01
     échelle
    -1.00
    <bos>
    -0.99
    Mvh
    -0.97
     REQUIRED
    -0.96
    MANUEL
    -0.96
    狨
    -0.93
    られていた
    -0.93
    一样的
    -0.93
    POSITIVE LOGITS
     caminar
    1.05
     What
    0.99
     Once
    0.91
     və
    0.91
     You
    0.90
     transcur
    0.88
     還
    0.87
     voorwaarden
    0.87
     on
    0.85
     There
    0.84
    Activations Density 0.001%

    No Known Activations