© 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. 38094
    Prev
    Next
    INDEX
    Explanations

    substance addiction recovery facility

    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
     Jahrh
    -0.87
     interesse
    -0.77
    !,
    -0.77
     mengumumkan
    -0.76
    vido
    -0.75
    Controls
    -0.75
    皮膚
    -0.73
    wt
    -0.73
    消失了
    -0.73
    mentar
    -0.72
    POSITIVE LOGITS
    Addiction
    1.27
     inpatient
    1.25
     addiction
    1.23
     Addiction
    1.16
     PHP
    1.13
     recovery
    1.00
     facility
    1.00
     substance
    0.95
     Recovery
    0.94
    Medication
    0.92
    Activations Density 0.009%

    No Known Activations