© 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. 31148
    Prev
    Next
    INDEX
    Explanations

    privately held or owned

    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
     धन
    -0.74
    ampilkan
    -0.74
    carea
    -0.70
     Vertra
    -0.67
    ichtliche
    -0.66
     Regierung
    -0.66
     wyposaż
    -0.65
    Tony
    -0.65
    仕
    -0.65
     Added
    -0.64
    POSITIVE LOGITS
     held
    4.94
    held
    3.88
    Held
    3.66
     Held
    3.50
     HELD
    2.91
     owned
    2.81
     possessed
    2.78
     déten
    2.45
     dimiliki
    2.19
    owned
    2.14
    Activations Density 0.077%

    No Known Activations