© 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. 10-GEMMASCOPE-RES-131K
    7. 1471
    Prev
    Next
    INDEX
    Explanations

    contact information

    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_10/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
     this
    -1.49
     Septembre
    -1.41
    sonder
    -1.32
    resten
    -1.30
     hvil
    -1.30
     if
    -1.29
     Octobre
    -1.24
     mostaza
    -1.23
     púb
    -1.20
     extérieures
    -1.20
    POSITIVE LOGITS
     Когда
    1.45
     delightfully
    1.41
     dreary
    1.37
     indescri
    1.35
     incont
    1.34
     number
    1.34
     nació
    1.28
     deliciously
    1.27
     incongru
    1.27
     dismal
    1.22
    Activations Density 0.024%

    No Known Activations