© 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. 60292
    Prev
    Next
    INDEX
    Explanations

    negative criticism or judgment

    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
     unsatisfactory
    -1.05
    onnen
    -0.96
    Composite
    -0.88
     étrange
    -0.85
    ष्ठ
    -0.84
     deplorable
    -0.83
     sentire
    -0.83
     panini
    -0.83
     cess
    -0.82
     pade
    -0.82
    POSITIVE LOGITS
     criticism
    1.33
     defensive
    1.14
     critic
    1.09
     critical
    1.04
     criticized
    1.01
    judgment
    1.01
     gossip
    1.00
     boss
    0.97
     critici
    0.96
    critic
    0.95
    Activations Density 0.027%

    No Known Activations