© 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. 66145
    Prev
    Next
    INDEX
    Explanations

    echo

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

    This neuron fires on first‐person self‐references (e.g. “I,” “I’d,” “I’ll”) in the text.

    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
     explains
    -0.88
     Explain
    -0.88
    поді
    -0.81
    lgica
    -0.78
     Includes
    -0.78
     Explains
    -0.77
    zji
    -0.76
    menistan
    -0.75
     explain
    -0.75
     YORK
    -0.73
    POSITIVE LOGITS
     echo
    4.22
     echoed
    3.80
    Echo
    3.52
    echo
    3.50
     echoes
    3.42
     echoing
    3.41
     Echo
    3.31
     second
    2.77
     ECHO
    2.50
     Echoes
    2.44
    Activations Density 0.020%

    No Known Activations