© 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. 70870
    Prev
    Next
    INDEX
    Explanations

    database keys and references

    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
     opleiding
    -1.15
     but
    -1.13
     reduzir
    -1.04
     seite
    -1.03
     joyería
    -1.03
    compromising
    -1.02
     desmotiv
    -0.99
     komende
    -0.99
     confirmó
    -0.98
     moviliz
    -0.98
    POSITIVE LOGITS
     by
    1.14
     thèse
    1.00
     defaultdict
    1.00
    hysema
    1.00
     personnage
    0.98
    IES
    0.98
    HA
    0.96
     canadienne
    0.96
    IN
    0.95
     nouvelle
    0.95
    Activations Density 0.004%

    No Known Activations