© 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. 93691
    Prev
    Next
    INDEX
    Explanations

    technical document labels

    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
    “…
    -1.13
    にします
    -0.95
     "...
    -0.95
    んですよ
    -0.94
     "..
    -0.92
    !!!!!!
    -0.92
    に行ってきました
    -0.92
     recherchez
    -0.90
    хнет
    -0.89
    !!!!!!!
    -0.88
    POSITIVE LOGITS
    常见的
    1.07
    もある
    1.04
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.98
    qJ
    0.95
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.95
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.94
    Ress
    0.93
    ⣉
    0.92
    ͋
    0.91
    起来的
    0.91
    Activations Density 0.222%

    No Known Activations