© 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. 118050
    Prev
    Next
    INDEX
    Explanations

    scientific papers and citations

    np_acts-logits-general · gemini-2.5-flash-lite

    academic paper abstract sections.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects the vertical‐bar formatting marker (the “|” used as a delimiter in the abstract sections).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     rád
    -0.91
    essége
    -0.88
    🔻
    -0.84
    Pozri
    -0.83
    Proč
    -0.82
    Iné
    -0.82
    accesorios
    -0.82
    россий
    -0.81
    uniqlo
    -0.81
    Výhody
    -0.81
    POSITIVE LOGITS
     citations
    0.83
    </sup>
    0.79
    </sub>
    0.79
    клы
    0.79
    情報は
    0.77
     lief
    0.75
     }}
    0.75
    imura
    0.75
    eters
    0.74
     justi
    0.74
    Activations Density 0.001%

    No Known Activations