© 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. 12207
    Prev
    Next
    INDEX
    Explanations

    boolean logic and returns

    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
    砼
    -0.91
    oléon
    -0.91
    tify
    -0.89
    鹌
    -0.89
     muttering
    -0.89
    GeneratedValue
    -0.87
    𐌾
    -0.84
     BEAUT
    -0.81
     doloroso
    -0.81
     adulte
    -0.79
    POSITIVE LOGITS
     answer
    0.93
     evaluation
    0.91
     absence
    0.86
     evaluate
    0.84
     implementation
    0.84
     Implementation
    0.84
     assume
    0.82
     listos
    0.82
     counting
    0.82
     assumed
    0.82
    Activations Density 0.006%

    No Known Activations