© 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. 40103
    Prev
    Next
    INDEX
    Explanations

    dialogue starters

    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
     kter
    -1.02
    ು
    -0.91
    ENTY
    -0.87
     cuchar
    -0.82
     uby
    -0.82
     scalars
    -0.80
    پر
    -0.79
     bricolaje
    -0.79
     bataille
    -0.77
     çeşit
    -0.77
    POSITIVE LOGITS
     übrigens
    0.92
     positiva
    0.85
     proposta
    0.85
    CIÓN
    0.84
     Gegensatz
    0.82
    IDADES
    0.82
     negativa
    0.82
    следование
    0.81
    ்கள்
    0.81
    犯罪
    0.80
    Activations Density 0.003%

    No Known Activations