© 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. 36579
    Prev
    Next
    INDEX
    Explanations

    proper nouns and code constructs

    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
     Désolé
    -1.16
     Método
    -1.02
     internetu
    -1.02
     terwijl
    -1.01
     zonder
    -1.01
     aidant
    -0.97
     På
    -0.95
     sufrió
    -0.94
     to
    -0.93
     pasará
    -0.93
    POSITIVE LOGITS
    Tensi
    0.94
    niejsze
    0.88
    IUCN
    0.88
    vatel
    0.87
    </em>
    0.87
    Redu
    0.86
    </h2>
    0.85
    对抗
    0.85
     singular
    0.84
     wipe
    0.84
    Activations Density 0.000%

    No Known Activations