© 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. 98326
    Prev
    Next
    INDEX
    Explanations

    lost, forgotten, or obscure

    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
    estroyer
    -0.96
    *///
    -0.92
     sudor
    -0.92
    芻
    -0.91
     quoc
    -0.90
     nearby
    -0.89
    albeit
    -0.88
    Besitos
    -0.88
     madu
    -0.88
     allerdings
    -0.85
    POSITIVE LOGITS
     forgotten
    2.27
     buried
    2.22
     obscurity
    2.11
    forgotten
    1.74
     relegated
    1.73
     oblivion
    1.72
     Forgotten
    1.50
    buried
    1.48
     lost
    1.47
     Buried
    1.46
    Activations Density 0.057%

    No Known Activations