© 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. 116749
    Prev
    Next
    INDEX
    Explanations

    questions with what/whether

    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
    NECTIONS
    -0.76
     TÜV
    -0.75
    벤
    -0.73
    ƪ
    -0.73
    >{@
    -0.73
     ReSharper
    -0.72
     Dried
    -0.71
     warunki
    -0.71
    jspx
    -0.71
    dias
    -0.71
    POSITIVE LOGITS
    abort
    1.11
     DB
    1.06
    DB
    1.03
     abort
    0.96
    activity
    0.87
     dd
    0.85
    $
    0.82
     $
    0.81
    return
    0.81
     session
    0.80
    Activations Density 0.007%

    No Known Activations