© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81382
    Prev
    Next
    INDEX
    Explanations

    late check-in/ -out

    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
    exam
    -0.76
    직
    -0.74
    iség
    -0.73
    inactive
    -0.72
    antwoorden
    -0.71
     corrections
    -0.71
    Contributions
    -0.71
    fts
    -0.71
    ellar
    -0.70
    bati
    -0.70
    POSITIVE LOGITS
     check
    2.28
     checkout
    2.28
    checkin
    2.17
     Check
    2.05
    CheckIn
    1.94
    Check
    1.92
     Checkout
    1.77
    checkout
    1.76
    checkOut
    1.65
    Checkout
    1.61
    Activations Density 0.023%

    No Known Activations