© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110452
    Prev
    Next
    INDEX
    Explanations

    development and poverty indices

    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
    BU
    -0.91
    Controls
    -0.88
    ffi
    -0.87
    BAR
    -0.85
     Controls
    -0.79
     tân
    -0.78
     Explain
    -0.76
    Explain
    -0.75
     smartphone
    -0.75
    Pere
    -0.75
    POSITIVE LOGITS
     poverty
    1.41
     Poverty
    1.35
    Poverty
    1.20
    poverty
    1.07
    stattung
    0.97
     Millennium
    0.93
    Attacking
    0.86
     millennium
    0.84
     Medium
    0.82
     pobreza
    0.82
    Activations Density 0.015%

    No Known Activations