© 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. 104840
    Prev
    Next
    INDEX
    Explanations

    common sequences or pairings

    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
    &:
    -1.25
     ungefär
    -1.22
     forment
    -1.21
    <?,
    -1.20
    >&
    -1.18
    ulu
    -1.18
     gdy
    -1.16
    −/−
    -1.16
    ->
    -1.16
     &
    -1.16
    POSITIVE LOGITS
     what
    1.68
     any
    1.42
     desnuda
    1.38
     szybko
    1.33
     rústica
    1.29
     creciente
    1.28
     promesas
    1.27
     cerrada
    1.26
     aimez
    1.23
    Following
    1.23
    Activations Density 0.297%

    No Known Activations