© 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. 109270
    Prev
    Next
    INDEX
    Explanations

    freedom of press and interference

    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
    child
    -0.80
     Referenzen
    -0.80
     children
    -0.78
    稲荷
    -0.76
     people
    -0.74
     ${
    -0.74
     pegawai
    -0.73
     zwykle
    -0.73
    も良い
    -0.72
     peoples
    -0.71
    POSITIVE LOGITS
     Cens
    1.09
     censorship
    1.04
     SAFETY
    0.99
     censor
    0.97
     Reporters
    0.95
    Attacks
    0.92
     freelancers
    0.91
     Attacks
    0.87
     safety
    0.86
     Barnabas
    0.85
    Activations Density 0.015%

    No Known Activations