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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118759
    Prev
    Next
    INDEX
    Explanations

    demographic and personal details

    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
     gil
    -0.98
     INCLUDES
    -0.90
    berian
    -0.87
     INGREDIENTS
    -0.85
     Inge
    -0.85
    Sziasztok
    -0.85
     "*"
    -0.83
    ]!='
    -0.82
    zeba
    -0.82
    ThroughAttribute
    -0.82
    POSITIVE LOGITS
     employment
    1.67
     income
    1.48
     years
    1.47
     currently
    1.28
     How
    1.27
     hours
    1.22
     marital
    1.21
     highest
    1.20
     previous
    1.20
     education
    1.18
    Activations Density 0.052%

    No Known Activations