© 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. 10-GEMMASCOPE-RES-131K
    7. 42315
    Prev
    Next
    INDEX
    Explanations

    co-evolution, transport, regulators

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

    terms with suffix patterns like "-ending", "-evolution", "-gulators", "-hibit", "-stim" - particularly scientific and technical terminology.

    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_10/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
    .
    -2.41
    纡
    -2.02
     bedeut
    -1.99
     minimizar
    -1.96
     acquire
    -1.94
     combinar
    -1.91
     limitar
    -1.84
     ausdrück
    -1.83
     conseguir
    -1.80
     wiederhol
    -1.80
    POSITIVE LOGITS
    
    2.39
     sprüche
    2.08
    
    2.02
    llavero
    1.91
    おかげ
    1.90
     صفحۀ
    1.81
    ︕
    1.77
     concernés
    1.71
    Ольга
    1.70
     marins
    1.69
    Activations Density 0.039%

    No Known Activations