© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 31938
    Prev
    Next
    INDEX
    Explanations

    end of phrase

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

    The neuron fires strongly on the main content words (especially key nouns) of a question or statement.

    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
     latter
    -1.29
     another
    -1.26
     This
    -1.16
    %,
    -1.12
     former
    -1.12
    $,
    -1.12
     that
    -1.11
     other
    -1.09
    }$,
    -1.05
     Ganzen
    -1.04
    POSITIVE LOGITS
    .");
    2.27
    .}
    2.14
    .]
    2.05
    .)
    2.00
    .")
    1.99
    .')
    1.94
    .");
    
    1.87
    .');
    1.83
    .")
    
    1.77
    .";
    1.75
    Activations Density 0.296%

    No Known Activations