© 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. 117820
    Prev
    Next
    INDEX
    Explanations

    destroying or leveling things

    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
     Hurt
    -0.93
     limiting
    -0.92
     Verlet
    -0.89
     được
    -0.88
    nuevo
    -0.88
    espero
    -0.87
     parry
    -0.87
     hindering
    -0.85
    hurt
    -0.85
    רה
    -0.85
    POSITIVE LOGITS
     destroy
    2.67
     destroys
    2.28
     destroyed
    2.17
     destroying
    2.06
    destroy
    2.00
     decim
    1.95
     destruction
    1.90
     Destroy
    1.89
     разру
    1.77
     уничто
    1.74
    Activations Density 0.075%

    No Known Activations