© 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. 81321
    Prev
    Next
    INDEX
    Explanations

    color codes and html attributes

    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
    mbggenerated
    -0.90
     deinen
    -0.84
     apenas
    -0.82
     podría
    -0.78
     berperan
    -0.77
    God
    -0.77
     nuestros
    -0.76
     Postgres
    -0.76
     faible
    -0.75
    atschapp
    -0.75
    POSITIVE LOGITS
     snowflakes
    0.87
    nasium
    0.85
    稷
    0.84
     Startseite
    0.84
    quake
    0.83
    Gossip
    0.82
    陷
    0.82
    мә
    0.82
     GRATU
    0.81
    cích
    0.80
    Activations Density 0.018%

    No Known Activations