© 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. 23764
    Prev
    Next
    INDEX
    Explanations

    buried or underground things and artifacts

    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
    ovala
    -0.83
     destroyers
    -0.82
    Gek
    -0.79
    ('');
    -0.78
     brooms
    -0.77
    ኝ
    -0.77
    )");
    -0.77
    โม
    -0.75
     "/",
    -0.74
    сунок
    -0.74
    POSITIVE LOGITS
     buried
    1.94
     underground
    1.32
     hidden
    1.31
    buried
    1.25
     unexplo
    1.18
     old
    1.15
     utilities
    1.13
     unknown
    1.12
     abandoned
    1.10
     artifacts
    1.07
    Activations Density 0.039%

    No Known Activations