© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118640
    Prev
    Next
    INDEX
    Explanations

    losing sight or track

    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
    Limitation
    -0.89
     новую
    -0.85
     الاد
    -0.82
    டுத்த
    -0.82
     Limitation
    -0.80
    よりは
    -0.79
    Diploma
    -0.79
     imperfection
    -0.78
    riendo
    -0.77
    又是
    -0.77
    POSITIVE LOGITS
     focus
    1.61
     original
    1.45
     loses
    1.34
     ursprünglichen
    1.28
     what
    1.27
     connection
    1.24
     ursprünglich
    1.23
     lost
    1.23
     sense
    1.16
    focus
    1.15
    Activations Density 0.035%

    No Known Activations