© 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. 97842
    Prev
    Next
    INDEX
    Explanations

    aggravating injuries

    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
    uminazione
    -0.79
    atnya
    -0.79
    ány
    -0.77
     naik
    -0.74
     baron
    -0.73
    ➡
    -0.72
     recupero
    -0.72
    Negocio
    -0.71
     Chateau
    -0.71
     Baruch
    -0.70
    POSITIVE LOGITS
     aggravating
    1.70
     aggravate
    1.63
     aggravated
    1.57
     tweaked
    1.55
     injuring
    1.47
     aggra
    1.40
     injure
    1.39
     rein
    1.33
     injured
    1.29
     tweak
    1.27
    Activations Density 0.034%

    No Known Activations