© 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. 47461
    Prev
    Next
    INDEX
    Explanations

    words relating to position and state

    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
     at
    -1.96
     almost
    -1.91
     when
    -1.91
     five
    -1.87
     two
    -1.86
     with
    -1.84
     for
    -1.83
     first
    -1.82
     after
    -1.81
     three
    -1.81
    POSITIVE LOGITS
    鵙
    2.03
     zoude
    2.02
    ఽ
    1.86
    镲
    1.85
    ܆
    1.83
     😊
    1.77
     😁
    1.71
     !!!!
    1.71
    commonly
    1.70
     dezelve
    1.70
    Activations Density 0.009%

    No Known Activations