© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106937
    Prev
    Next
    INDEX
    Explanations

    git commit SHA

    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
     unmet
    -0.80
    angnya
    -0.78
    nium
    -0.77
    黄金
    -0.77
    Powell
    -0.76
     reconno
    -0.75
    ubernetes
    -0.75
    ecal
    -0.75
    的眼
    -0.75
    BIÉN
    -0.73
    POSITIVE LOGITS
     SHA
    1.13
    SHA
    1.06
     sha
    1.06
    Sha
    0.99
     Sha
    0.98
     Author
    0.93
    sha
    0.92
     Commit
    0.89
     Message
    0.88
    rev
    0.88
    Activations Density 0.040%

    No Known Activations