© 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. 90167
    Prev
    Next
    INDEX
    Explanations

    delusions and hallucinations

    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
    YON
    -0.82
    fseek
    -0.81
    IZEN
    -0.81
    abstractmethod
    -0.78
     Poni
    -0.78
    轼
    -0.77
    ílio
    -0.75
     Slat
    -0.73
    筆
    -0.71
    MERCE
    -0.71
    POSITIVE LOGITS
     paranoid
    3.03
     paranoia
    3.00
    paran
    2.27
     delusions
    2.22
     Paran
    2.00
    Paran
    1.89
     delusion
    1.87
     hallucinations
    1.82
     delusional
    1.80
     halluc
    1.75
    Activations Density 0.054%

    No Known Activations