© 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. 12178
    Prev
    Next
    INDEX
    Explanations

    conjunction followed by noun descriptor

    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
     its
    -1.34
    things
    -1.12
    ין
    -1.09
    ₂,
    -1.09
     jeho
    -1.08
    >,
    -1.05
     både
    -1.05
    >>,
    -1.05
    をはじめ
    -1.02
    ³/
    -1.02
    POSITIVE LOGITS
     the
    1.19
     characteristics
    1.06
    ために
    1.05
     extent
    1.04
     eventual
    0.98
    (*^^
    0.96
    白石
    0.95
     probable
    0.94
    ようです
    0.91
     location
    0.91
    Activations Density 0.109%

    No Known Activations