© 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. 22-GEMMASCOPE-RES-131K
    7. 12472
    Prev
    Next
    INDEX
    Explanations

    cost prices fees

    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_22/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
     other
    -1.54
     many
    -1.51
     more
    -1.36
     numerous
    -1.32
     several
    -1.30
     important
    -1.28
     at
    -1.23
     dozens
    -1.22
     it
    -1.18
     some
    -1.18
    POSITIVE LOGITS
    depending
    1.48
     chaussures
    1.39
     blessures
    1.34
     faſt
    1.30
    𓆏
    1.26
     serre
    1.23
     triom
    1.21
     coûts
    1.19
     varier
    1.14
     contenus
    1.13
    Activations Density 0.026%

    No Known Activations