© 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. 11241
    Prev
    Next
    INDEX
    Explanations

    programming language keywords and identifiers

    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
     Atención
    -1.29
    opie
    -1.28
    maintain
    -1.11
    topf
    -1.09
    teries
    -1.08
     podrob
    -1.07
    insatz
    -1.06
     Dinas
    -1.05
    eload
    -1.05
    detailed
    -1.04
    POSITIVE LOGITS
     from
    1.52
     people
    1.48
     in
    1.20
     many
    1.16
     any
    1.11
     activities
    1.10
     on
    1.08
     out
    1.06
     time
    1.05
     constantly
    1.05
    Activations Density 0.013%

    No Known Activations