© 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. 32353
    Prev
    Next
    INDEX
    Explanations

    not or no followed by a verb phrase

    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
     disappro
    -0.81
    頑張
    -0.79
    Odd
    -0.77
     conseillers
    -0.76
     Dami
    -0.76
     всю
    -0.75
    унд
    -0.75
    })^
    -0.74
     интерьера
    -0.74
     vẫn
    -0.73
    POSITIVE LOGITS
     panic
    1.31
     panicked
    0.97
     many
    0.94
    panic
    0.90
     fear
    0.87
    fraid
    0.85
     easy
    0.83
     concern
    0.82
     Cristina
    0.79
    chronic
    0.75
    Activations Density 0.034%

    No Known Activations