© 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. 73879
    Prev
    Next
    INDEX
    Explanations

    struggles and emotional journeys

    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
     Attila
    -0.94
     satan
    -0.94
    跻
    -0.93
     diablo
    -0.91
    转发
    -0.90
     voodoo
    -0.89
    lif
    -0.88
    沥
    -0.87
     cpf
    -0.85
     introdu
    -0.84
    POSITIVE LOGITS
    成长
    1.12
     perigo
    1.12
     emotional
    1.08
     avião
    1.04
     leadership
    1.04
     herói
    1.01
     his
    1.00
    視聴
    0.98
     lixo
    0.98
     freio
    0.97
    Activations Density 0.024%

    No Known Activations