© 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. 45278
    Prev
    Next
    INDEX
    Explanations

    code and markup declarations

    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
    rouwen
    -0.94
    哉
    -0.93
     Two
    -0.93
     Один
    -0.89
    しよう
    -0.88
     Kuchen
    -0.88
     tumbuh
    -0.85
     TWO
    -0.84
     Kecamatan
    -0.84
    classifiers
    -0.84
    POSITIVE LOGITS
     DBS
    0.86
    verhältnisse
    0.85
    よりも
    0.84
     Angabe
    0.83
    essions
    0.81
     пола
    0.80
     möglichst
    0.79
    뭄
    0.78
    ᾿
    0.77
     trucos
    0.76
    Activations Density 0.000%

    No Known Activations