© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89697
    Prev
    Next
    INDEX
    Explanations

    web development code and markup

    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
     Skyrim
    -0.84
    ="./
    -0.80
    glBegin
    -0.79
     Hao
    -0.77
     Mendelssohn
    -0.74
    ilibre
    -0.73
    keley
    -0.72
    vik
    -0.72
     температуре
    -0.72
    🦚
    -0.71
    POSITIVE LOGITS
     occured
    0.86
    ="{{
    0.81
     }}"
    0.77
     Zwar
    0.77
     tertutup
    0.77
     what
    0.77
    ablemente
    0.76
    peper
    0.75
    ùa
    0.74
    пуляр
    0.73
    Activations Density 0.004%

    No Known Activations