© 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. 11471
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     bicchiere
    -0.99
    ⿵
    -0.96
     précédents
    -0.93
    javac
    -0.90
     亮
    -0.90
    gangss
    -0.88
    ⿸
    -0.88
    之后
    -0.87
    gerichte
    -0.86
    hatenablog
    -0.86
    POSITIVE LOGITS
     other
    1.08
     mesures
    1.01
    搀
    0.95
     []),
    0.92
    ebly
    0.92
    iroz
    0.91
    なります
    0.90
    的其他
    0.88
    车的
    0.85
     poursuite
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.