© 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. 90336
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns

    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
     which
    -1.52
     both
    -1.21
     superbly
    -1.15
     could
    -1.13
     may
    -1.13
     effectively
    -1.13
     as
    -1.12
     an
    -1.10
     in
    -1.08
     or
    -1.08
    POSITIVE LOGITS
     incontri
    1.34
     preghi
    1.30
     alguns
    1.30
     любого
    1.30
    still
    1.29
     accogli
    1.25
     pensare
    1.22
    依然
    1.20
     foglie
    1.19
     dieci
    1.17
    Activations Density 0.007%

    No Known Activations