© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 75063
    Prev
    Next
    INDEX
    Explanations

    agency or origin

    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
     by
    -1.06
     creating
    -0.97
     establish
    -0.97
     extraordinary
    -0.94
     extraordinarily
    -0.92
     spurred
    -0.88
     making
    -0.87
     замі
    -0.87
     undeniably
    -0.86
     liquidated
    -0.85
    POSITIVE LOGITS
     whom
    1.13
     who
    1.09
    actéristi
    1.06
     privind
    1.05
     AWAY
    1.03
     DURING
    1.02
     THROUGH
    1.00
    蛱
    1.00
    modium
    0.99
    mmation
    0.98
    Activations Density 0.092%

    No Known Activations