© 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. 10-GEMMASCOPE-RES-131K
    7. 39510
    Prev
    Next
    INDEX
    Explanations

    Python libraries and frameworks

    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_10/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
     Also
    -1.85
     one
    -1.70
     When
    -1.65
    In
    -1.62
     While
    -1.57
    of
    -1.55
     receive
    -1.53
    While
    -1.52
    geoning
    -1.51
     have
    -1.49
    POSITIVE LOGITS
    Baru
    1.39
    齜
    1.38
     lefs
    1.37
    meng
    1.36
     ..........
    1.34
    towards
    1.32
    樯
    1.30
    撄
    1.30
     aldı
    1.30
     rospy
    1.30
    Activations Density 0.040%

    No Known Activations