© 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. 80886
    Prev
    Next
    INDEX
    Explanations

    of [concept]

    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
     dépens
    -1.21
     plafon
    -1.21
     maksi
    -1.17
     éché
    -1.16
     délais
    -1.16
     juft
    -1.15
     spécialement
    -1.14
     felpa
    -1.13
     lumine
    -1.13
     excès
    -1.13
    POSITIVE LOGITS
     what
    1.69
     an
    1.55
     as
    1.48
     without
    1.45
     three
    1.44
     at
    1.41
     not
    1.36
     after
    1.35
     four
    1.34
     a
    1.33
    Activations Density 0.036%

    No Known Activations