© 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. 34-GEMMASCOPE-RES-131K
    4. 60024
    Prev
    Next
    INDEX
    Explanations

    getting into a state

    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_34/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
     douleurs
    -0.93
     få
    -0.93
     búsqueda
    -0.91
    ihara
    -0.91
    kiem
    -0.90
    Warna
    -0.89
    varande
    -0.89
     membuatnya
    -0.89
    数
    -0.88
     ficción
    -0.87
    POSITIVE LOGITS
     into
    1.84
     rid
    1.71
     involved
    1.20
     acquainted
    1.20
     influenced
    1.07
     onto
    1.00
     ready
    0.99
     convinced
    0.96
     hold
    0.95
     closer
    0.95
    Activations Density 0.046%

    No Known Activations