© 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. 83403
    Prev
    Next
    INDEX
    Explanations

    political writing, news analysis

    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
     apel
    -0.88
    Chromosome
    -0.80
    Sodium
    -0.80
    FromDB
    -0.79
     vocale
    -0.78
    Sensory
    -0.75
    Sensor
    -0.74
    therapie
    -0.73
    RATES
    -0.73
    gebied
    -0.73
    POSITIVE LOGITS
     political
    2.31
     Political
    2.06
    Political
    1.98
    political
    1.96
    政治
    1.82
     politics
    1.78
     Politics
    1.75
     politico
    1.64
     político
    1.61
     Capitol
    1.60
    Activations Density 0.115%

    No Known Activations