© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 54092
    Prev
    Next
    INDEX
    Explanations

    code fragments 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
     would
    -1.47
     this
    -1.33
     samochód
    -1.21
     already
    -1.18
     school
    -1.18
     created
    -1.12
     дошко
    -1.09
     found
    -1.09
     our
    -1.08
     certainly
    -1.08
    POSITIVE LOGITS
     améliorer
    1.40
     menjalani
    1.23
     dégustation
    1.19
     menghubungi
    1.19
     traducciones
    1.14
     procéder
    1.13
     weihnachten
    1.13
    衄
    1.12
     terjun
    1.12
    nemia
    1.10
    Activations Density 0.001%

    No Known Activations