© 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. 104724
    Prev
    Next
    INDEX
    Explanations

    Be aware

    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
     máme
    -1.16
     télécommande
    -1.16
    endaftaran
    -1.13
    HomeComponent
    -1.10
    月は
    -1.08
    🐠
    -1.07
    мать
    -1.06
     portátiles
    -1.06
     Divulgação
    -1.06
    nivå
    -1.06
    POSITIVE LOGITS
     also
    1.50
     you
    1.47
    <eos>
    1.30
     allerdings
    1.20
    прочем
    1.16
     البته
    1.12
     use
    1.09
     even
    1.07
     further
    1.05
     toutefois
    1.02
    Activations Density 0.092%

    No Known Activations