© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38343
    Prev
    Next
    INDEX
    Explanations

    man's name or description

    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
     itself
    -1.12
    無い
    -1.05
    䊉
    -0.99
    arlı
    -0.97
    ὲν
    -0.96
     einschließlich
    -0.95
     hauptsächlich
    -0.94
     female
    -0.93
     rele
    -0.91
     innych
    -0.90
    POSITIVE LOGITS
     who
    1.60
    folk
    1.22
     plafon
    1.20
    hunt
    1.19
     man
    1.16
     issus
    1.13
     parcours
    1.13
     parut
    1.12
     contenu
    1.11
     mxArray
    1.10
    Activations Density 0.035%

    No Known Activations