Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8673
    Prev
    Next
    INDEX
    Explanations

    Chinese food and internet censorship

    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
     Mutations
    -0.81
    cal
    -0.81
     yun
    -0.76
     blackish
    -0.75
     乗り
    -0.72
     a
    -0.71
    Хоро
    -0.70
     zhu
    -0.69
     Fei
    -0.69
     Cui
    -0.68
    POSITIVE LOGITS
     routine
    0.88
    skrift
    0.87
     болез
    0.83
     recommandé
    0.82
     reconnaît
    0.80
    poche
    0.79
     Praga
    0.79
    diven
    0.79
    zące
    0.79
     Benedikt
    0.79
    Activations Density 0.009%

    No Known Activations