© 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. 107739
    Prev
    Next
    INDEX
    Explanations

    long absence or hiatus

    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
     continue
    -1.21
     continues
    -1.10
     still
    -1.05
     continued
    -0.95
     at
    -0.92
     continuar
    -0.91
     continuing
    -0.90
     this
    -0.89
     ještě
    -0.88
    логических
    -0.87
    POSITIVE LOGITS
     hiatus
    2.95
     absence
    2.17
     inactivity
    1.83
     Absence
    1.68
     отсут
    1.63
    Absence
    1.61
    absence
    1.59
     absent
    1.58
     gap
    1.55
     dormant
    1.54
    Activations Density 0.078%

    No Known Activations