© 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. 97726
    Prev
    Next
    INDEX
    Explanations

    mouse click drag hover

    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
     Fea
    -0.88
     ATTACK
    -0.85
    uglify
    -0.84
    Ensuite
    -0.82
     Fuku
    -0.80
    QPushButton
    -0.79
     allege
    -0.79
    ensitivity
    -0.79
     Provo
    -0.79
     Gameplay
    -0.78
    POSITIVE LOGITS
     dragged
    0.81
     Passive
    0.71
     сумка
    0.70
    kais
    0.69
    ädchen
    0.69
     drag
    0.69
    掾
    0.68
     seamlessly
    0.66
    Passive
    0.66
     passive
    0.65
    Activations Density 0.056%

    No Known Activations