© 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. 115747
    Prev
    Next
    INDEX
    Explanations

    recruited enlisted drafted

    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
    Mez
    -0.93
    довал
    -0.78
    жность
    -0.78
     Supported
    -0.78
    Fuckin
    -0.76
     سكانية
    -0.76
     محبوب
    -0.75
     remplacé
    -0.74
     اظهار
    -0.73
    Возможно
    -0.73
    POSITIVE LOGITS
     pressed
    2.52
     recruited
    2.42
     enlisted
    2.05
    pressed
    2.03
     press
    1.92
    Press
    1.90
    Pressed
    1.88
     Press
    1.86
    press
    1.84
     drafted
    1.84
    Activations Density 0.075%

    No Known Activations