© 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. 109764
    Prev
    Next
    INDEX
    Explanations

    world's superlative descriptors

    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
    Brainz
    -1.43
    子は
    -1.23
     masjid
    -1.21
    塒
    -1.21
     neigh
    -1.20
    quido
    -1.20
    çalves
    -1.20
     tiss
    -1.20
    した場合
    -1.20
     protégé
    -1.19
    POSITIVE LOGITS
     largest
    1.74
     most
    1.50
     greatest
    1.48
     "
    1.45
    "
    1.44
     finest
    1.38
     premier
    1.36
     biggest
    1.34
     best
    1.33
     foremost
    1.31
    Activations Density 0.035%

    No Known Activations