© 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. 119107
    Prev
    Next
    INDEX
    Explanations

    programming support database http

    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
    ubourg
    -0.96
     Meksi
    -0.92
     krim
    -0.88
     diserta
    -0.85
    クタイ
    -0.84
    mẫu
    -0.82
    Perm
    -0.82
     Lü
    -0.82
     Ольга
    -0.82
    isissez
    -0.82
    POSITIVE LOGITS
     SUPPORT
    1.34
    Support
    1.30
     support
    1.13
     Support
    1.13
     Database
    1.06
    SUPPORT
    1.02
    support
    1.02
    database
    0.98
    Http
    0.90
    Database
    0.89
    Activations Density 0.003%

    No Known Activations