© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84441
    Prev
    Next
    INDEX
    Explanations

    relationships and friendships

    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
     using
    -1.05
    shared
    -0.88
     on
    -0.87
     of
    -0.87
     about
    -0.87
     perfectly
    -0.85
     taking
    -0.85
    共有
    -0.85
     hitting
    -0.83
     or
    -0.82
    POSITIVE LOGITS
     forged
    1.35
    hips
    1.14
    relationships
    1.14
    llllll
    1.14
     relationships
    1.01
    forged
    1.01
    知り
    1.00
    outside
    1.00
     OUTSIDE
    0.99
    developed
    0.98
    Activations Density 0.017%

    No Known Activations