© 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. 67335
    Prev
    Next
    INDEX
    Explanations

    assignment of state

    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
     nouveautés
    -1.02
     sélections
    -0.95
     ADULT
    -0.94
    ochrom
    -0.94
    强大的
    -0.93
     difficultés
    -0.93
     superbes
    -0.93
     défis
    -0.92
     tibur
    -0.92
     parámetros
    -0.91
    POSITIVE LOGITS
     being
    1.10
     participate
    1.07
     Being
    1.03
     assigned
    1.01
     participates
    1.00
     neuen
    0.97
     participar
    0.93
     participating
    0.92
     contribute
    0.91
     verschiedene
    0.88
    Activations Density 0.030%

    No Known Activations