© 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. 78291
    Prev
    Next
    INDEX
    Explanations

    assignment statements and function definitions

    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
     what
    -1.02
     interessieren
    -0.91
     important
    -0.91
     merec
    -0.88
    ysl
    -0.88
     both
    -0.87
     appropriate
    -0.87
    jangkau
    -0.86
     any
    -0.85
     äl
    -0.85
    POSITIVE LOGITS
    such
    1.16
    une
    1.00
     solche
    0.98
    temp
    0.96
    =(
    0.96
     =
    0.95
    這樣
    0.95
     canadian
    0.90
    这样的
    0.89
    still
    0.87
    Activations Density 0.004%

    No Known Activations