© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118069
    Prev
    Next
    INDEX
    Explanations

    eliminating unwanted 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
     causando
    -0.90
     Schleswig
    -0.88
     Drit
    -0.86
    enz
    -0.84
     anticor
    -0.83
     tropics
    -0.83
     morons
    -0.82
    óg
    -0.80
     defoli
    -0.80
     rans
    -0.80
    POSITIVE LOGITS
     unwanted
    1.84
     undesirable
    1.34
     stubborn
    1.32
     bad
    1.30
     excess
    1.28
     undes
    1.26
     stratég
    1.15
     konkrét
    1.14
     både
    1.11
     Meksi
    1.09
    Activations Density 0.094%

    No Known Activations