© 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. 26065
    Prev
    Next
    INDEX
    Explanations

    affiliates. Honeoye. Brokenhearted

    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
     it
    -1.22
     berle
    -1.03
     salvador
    -0.96
    才有
    -0.96
     gorra
    -0.96
     propor
    -0.95
     genero
    -0.95
     relatie
    -0.94
    総評
    -0.93
     uska
    -0.93
    POSITIVE LOGITS
     farmers
    1.01
    ата
    0.94
     gehört
    0.94
    jango
    0.93
     holiness
    0.93
     cukru
    0.93
    weiß
    0.92
    oughed
    0.91
     unravel
    0.91
    italian
    0.91
    Activations Density 0.001%

    No Known Activations