© 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. 22-GEMMASCOPE-RES-131K
    7. 71306
    Prev
    Next
    INDEX
    Explanations

    found in locations

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

    The neuron fires on instances of the copular or linking form “is” (including its ’s contraction) and similar factual “to be” statements (e.g. “is found”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ingeki
    -0.93
     four
    -0.88
     Holes
    -0.87
    そうですね
    -0.87
    評論
    -0.85
     consists
    -0.84
     artikke
    -0.82
     Như
    -0.82
     one
    -0.82
     referido
    -0.82
    POSITIVE LOGITS
     idolatry
    0.88
    ってる
    0.84
     László
    0.83
    MAGAZINE
    0.83
    räck
    0.82
     未来
    0.81
    EXCHANGE
    0.80
    ︕
    0.79
    über
    0.79
    롯
    0.79
    Activations Density 0.006%

    No Known Activations