© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31196
    Prev
    Next
    INDEX
    Explanations

    scala programming language concepts

    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
     noOf
    -0.81
     vettore
    -0.78
    DECLARE
    -0.75
     Medicaid
    -0.74
    кай
    -0.73
    idas
    -0.72
     Bangor
    -0.71
     پرس
    -0.71
    ográ
    -0.70
    struktion
    -0.69
    POSITIVE LOGITS
     vermelha
    0.91
    compan
    0.81
    bdb
    0.80
    мом
    0.73
    lamp
    0.72
    イルド
    0.71
    responsible
    0.70
    laint
    0.69
    ipad
    0.69
     scala
    0.67
    Activations Density 0.042%

    No Known Activations