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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27072
    Prev
    Next
    INDEX
    Explanations

    hypotheses and theories

    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_22/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
     pageIndex
    -1.16
    hafen
    -1.10
     христи
    -0.96
     pageNum
    -0.95
    Usage
    -0.95
     pož
    -0.94
     ketika
    -0.93
    bücher
    -0.93
     pageNo
    -0.93
     decisión
    -0.92
    POSITIVE LOGITS
     explanation
    1.94
     explanations
    1.56
     theory
    1.54
     explain
    1.48
     explaining
    1.48
     hypothesis
    1.45
     theories
    1.41
     hypotheses
    1.37
     proposed
    1.35
     reasons
    1.29
    Activations Density 0.145%

    No Known Activations