© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117094
    Prev
    Next
    INDEX
    Explanations

    home care and agencies

    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
    writeln
    -0.90
    醸
    -0.81
    バー
    -0.75
    ortic
    -0.74
     hotel
    -0.73
     Warrant
    -0.73
    ญ
    -0.72
     entfernt
    -0.72
    机
    -0.70
     tournoi
    -0.69
    POSITIVE LOGITS
     caregiver
    1.57
     caregivers
    1.51
     agency
    1.49
     clients
    1.45
     home
    1.38
     client
    1.37
     Agency
    1.31
    agency
    1.29
     visits
    1.27
     care
    1.24
    Activations Density 0.034%

    No Known Activations