© 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. 7241
    Prev
    Next
    INDEX
    Explanations

    ruin, sabotage, undermine, derail

    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
    よりは
    -1.17
    だけではなく
    -1.09
     nouvelles
    -1.08
     différents
    -1.06
     différentes
    -1.05
     allerlei
    -1.05
     distintos
    -1.03
     lämp
    -1.02
    Cura
    -1.02
     verschillende
    -1.01
    POSITIVE LOGITS
     attempts
    2.25
     efforts
    2.23
     already
    2.09
     ability
    1.99
    せっかく
    1.90
     attempt
    1.82
     valuable
    1.81
     intended
    1.80
     carefully
    1.77
     delicate
    1.72
    Activations Density 0.092%

    No Known Activations