© 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. 22-GEMMASCOPE-RES-131K
    7. 35830
    Prev
    Next
    INDEX
    Explanations

    continuation or repetition

    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
    deutschen
    -0.85
     Aufbau
    -0.85
     Anxiety
    -0.81
    gewöhn
    -0.81
    autre
    -0.81
     varandra
    -0.81
     pantolon
    -0.80
     שאי
    -0.80
    יצד
    -0.80
    ÁCT
    -0.80
    POSITIVE LOGITS
     again
    2.42
     still
    1.90
    again
    1.72
     continues
    1.70
     continue
    1.59
     continued
    1.57
    再次
    1.55
    Again
    1.53
     weiterhin
    1.52
     continuing
    1.51
    Activations Density 0.026%

    No Known Activations