© 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. 75179
    Prev
    Next
    INDEX
    Explanations

    database query operations

    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
     the
    -1.05
     bawat
    -0.89
     principalmente
    -0.87
     εικό
    -0.87
     безопасности
    -0.84
     cognac
    -0.83
    inher
    -0.83
     Startseite
    -0.82
     njia
    -0.82
     débris
    -0.82
    POSITIVE LOGITS
     sensaciones
    1.07
     antiguas
    1.06
     attribué
    1.01
     trabajado
    0.98
    𓂃
    0.98
    𓈒
    0.97
     reflexiones
    0.97
    ویش
    0.96
    больше
    0.95
    RAHAM
    0.94
    Activations Density 0.003%

    No Known Activations