© 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. 75205
    Prev
    Next
    INDEX
    Explanations

    Burren, Glutamine

    np_acts-logits-general · gemini-2.5-flash-lite

    code diff syntax with @@ markers and line numbers.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Hvem
    -1.48
    Jako
    -1.46
     sué
    -1.37
    Prí
    -1.35
    Tento
    -1.34
    Flere
    -1.34
     fasse
    -1.33
    Kolor
    -1.31
    Odpo
    -1.31
    Podob
    -1.30
    POSITIVE LOGITS
     —
    1.17
    ]
    1.09
     –
    1.09
        
    1.08
     avaliar
    1.04
    ro
    1.03
    大部分
    1.03
    </i>
    1.03
    وجد
    1.02
                
    1.01
    Activations Density 0.003%

    No Known Activations