© 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. 80781
    Prev
    Next
    INDEX
    Explanations

    sleep quality and timing

    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
    ála
    -0.81
    dbs
    -0.75
    แห
    -0.74
     Gok
    -0.73
     kne
    -0.73
     drying
    -0.72
     Lax
    -0.70
     Spas
    -0.69
    克服
    -0.69
    CIF
    -0.68
    POSITIVE LOGITS
    ANGES
    1.02
    álja
    0.94
     insufficient
    0.91
    nadequate
    0.91
    architecte
    0.90
    ufficient
    0.88
     optimal
    0.86
     teenagers
    0.85
     curtailed
    0.85
     duration
    0.85
    Activations Density 0.023%

    No Known Activations