© 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. 22-GEMMASCOPE-RES-131K
    7. 25565
    Prev
    Next
    INDEX
    Explanations

    advocacy chair

    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_22/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
     if
    -0.98
    Another
    -0.89
     they
    -0.89
     when
    -0.88
    剧照
    -0.87
     should
    -0.85
     all
    -0.83
    Finally
    -0.83
    욱
    -0.82
    okia
    -0.81
    POSITIVE LOGITS
     leadership
    1.33
     advocacy
    1.08
     chair
    1.05
     blogging
    1.04
    teness
    1.02
    ǵ
    1.00
    IONE
    0.99
    donc
    0.96
     blogs
    0.93
    ellate
    0.92
    Activations Density 0.066%

    No Known Activations