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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64457
    Prev
    Next
    INDEX
    Explanations

    events came to pass

    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
    "]]
    -0.89
     Become
    -0.86
     ちゃ
    -0.85
    become
    -0.85
    Become
    -0.85
    "}}
    -0.84
    Essa
    -0.84
    穣
    -0.84
    něte
    -0.83
    🧀
    -0.82
    POSITIVE LOGITS
     came
    4.72
     comes
    4.34
     come
    3.92
     occurred
    3.39
     occurs
    3.16
     coming
    3.00
     occur
    2.95
    came
    2.84
     datang
    2.77
    Came
    2.66
    Activations Density 0.103%

    No Known Activations