© 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. 34-GEMMASCOPE-RES-131K
    7. 117933
    Prev
    Next
    INDEX
    Explanations

    recognizing word patterns

    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_34/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
    گاهی
    -0.68
    зит
    -0.68
     trattano
    -0.67
    ꯦ
    -0.66
    strconv
    -0.66
     لیگ
    -0.66
    lineWidth
    -0.65
     láp
    -0.64
    grads
    -0.64
     Kramer
    -0.64
    POSITIVE LOGITS
     pattern
    7.41
     patterns
    6.72
    pattern
    6.38
     Pattern
    5.84
    Pattern
    5.69
     Patterns
    5.59
    patterns
    5.56
    Patterns
    5.31
     PATTERN
    5.13
    PATTERN
    5.06
    Activations Density 0.316%

    No Known Activations