© 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. 10-GEMMASCOPE-RES-131K
    4. 25
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns or earning

    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_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
     únicas
    -1.48
     nutrientes
    -1.34
     aplicar
    -1.33
     afectadas
    -1.25
    Incorrect
    -1.24
    ","+
    -1.23
    :'',
    -1.22
     urgencia
    -1.20
     nødvendig
    -1.20
    тель
    -1.19
    POSITIVE LOGITS
     inconce
    1.49
    서는
    1.49
    枼
    1.40
     Instead
    1.35
    ly
    1.34
    砹
    1.31
     intrigu
    1.31
    8
    1.29
     Polícia
    1.28
     instead
    1.27
    Activations Density 0.014%

    No Known Activations