© 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. 12518
    Prev
    Next
    INDEX
    Explanations

    specific noun phrases

    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
     اللون
    -0.93
     Beweis
    -0.88
    ginous
    -0.85
     personnalisés
    -0.85
    ][$
    -0.84
    IsValid
    -0.83
    Teal
    -0.83
     województwie
    -0.83
    广场
    -0.82
    ólogos
    -0.82
    POSITIVE LOGITS
     they
    0.92
    δος
    0.92
     желание
    0.88
     Respond
    0.85
    八年
    0.85
     guy
    0.84
     chiedere
    0.84
     کری
    0.83
     réponses
    0.82
    aré
    0.82
    Activations Density 0.036%

    No Known Activations