© 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. 117430
    Prev
    Next
    INDEX
    Explanations

    way of doing or being

    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
     strategies
    -0.86
     zosta
    -0.83
    invocation
    -0.79
     strategy
    -0.79
     concurs
    -0.76
     FIGURE
    -0.75
     Capacidad
    -0.75
     concurred
    -0.74
    ツール
    -0.74
    aları
    -0.74
    POSITIVE LOGITS
     of
    2.44
     thinking
    1.50
     doing
    1.32
     viewing
    1.16
    thinking
    1.02
    сный
    0.98
     things
    0.95
     seeing
    0.89
     Way
    0.88
     approaching
    0.88
    Activations Density 0.023%

    No Known Activations