© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50288
    Prev
    Next
    INDEX
    Explanations

    finding myself and others

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

    The neuron fires on Russian personal‐reference words—especially first‐person pronouns like “я” and other human‐referent terms.

    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
    )}
    
    -1.06
     and
    -1.02
    )});
    -1.01
     trzeba
    -1.00
    ();
    -0.97
     werden
    -0.94
    ksamkeit
    -0.93
    )();
    -0.93
    纽约
    -0.91
    }$,
    -0.91
    POSITIVE LOGITS
     jaro
    1.05
    って思
    1.05
     sedi
    1.04
     tricot
    1.03
     brisa
    1.01
     Zeits
    1.01
    salle
    1.00
    もあって
    0.98
     tempes
    0.98
     tille
    0.97
    Activations Density 0.010%

    No Known Activations