© 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. 65342
    Prev
    Next
    INDEX
    Explanations

    Ber names and places

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

    This neuron activates on tokens that begin with the letter sequence “Ber.”

    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
    などが
    -1.31
    などを
    -1.22
    などは
    -1.02
     penggunaan
    -1.00
    を
    -0.99
     kriminal
    -0.94
    と
    -0.93
    も
    -0.92
    それを
    -0.91
    ◞
    -0.91
    POSITIVE LOGITS
    monės
    1.11
    えっ
    1.08
    つづく
    1.08
    ところに
    1.03
    ごめん
    1.01
     deserved
    1.01
     varying
    1.01
    久し
    0.98
    Недоліки
    0.96
    monių
    0.96
    Activations Density 0.001%

    No Known Activations