© 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. 116738
    Prev
    Next
    INDEX
    Explanations

    social services and support

    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
    tacular
    -0.91
    rrrrrrrr
    -0.88
    vertising
    -0.88
    aaaaaa
    -0.88
    rrrrrr
    -0.86
    hhhhh
    -0.85
    ledad
    -0.84
    mth
    -0.83
     getWidth
    -0.82
    rrrrr
    -0.81
    POSITIVE LOGITS
     employment
    1.61
     food
    1.60
     job
    1.50
     health
    1.35
     transportation
    1.30
     access
    1.27
     financial
    1.27
     nutrition
    1.27
     housing
    1.23
     clothing
    1.19
    Activations Density 0.021%

    No Known Activations