© 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. 64340
    Prev
    Next
    INDEX
    Explanations

    negative behaviors or qualities

    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
     gracilis
    -0.96
     суток
    -0.94
     suitable
    -0.91
     wisely
    -0.90
     gelungen
    -0.86
     discreet
    -0.86
    Анна
    -0.86
    落在
    -0.85
     régl
    -0.85
    Identifying
    -0.84
    POSITIVE LOGITS
     behavior
    1.73
     behaviour
    1.48
     tendencies
    1.32
    ness
    1.31
    behavior
    1.29
     disregard
    1.24
     davran
    1.14
     and
    1.11
    ly
    1.05
    NESS
    1.02
    Activations Density 0.035%

    No Known Activations