© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49634
    Prev
    Next
    INDEX
    Explanations

    open neighborhoods

    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
     scaring
    -0.87
     unspeak
    -0.84
    setTime
    -0.83
     церемо
    -0.82
    GroupLayout
    -0.82
     účast
    -0.82
    espé
    -0.81
    TIMER
    -0.78
     controversi
    -0.78
     сильно
    -0.78
    POSITIVE LOGITS
     defective
    0.95
     txn
    0.84
     cittadini
    0.82
    UALLY
    0.81
     Cauchy
    0.81
     students
    0.81
     irra
    0.81
     Slayer
    0.80
     open
    0.79
     Thron
    0.79
    Activations Density 0.101%

    No Known Activations