© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 67978
    Prev
    Next
    INDEX
    Explanations

    guess

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

    The neuron strongly activates on the phrase “I guess.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    焄
    -2.53
    ࿚
    -2.19
    ]$
    -2.05
    تحميل
    -1.77
    許多
    -1.74
    神器
    -1.74
     Verordnung
    -1.74
     Bücher
    -1.70
     lutego
    -1.69
    它的
    -1.67
    POSITIVE LOGITS
     they
    2.91
    橚
    1.87
     technically
    1.83
    $
    1.81
    一瞬
    1.80
    今でも
    1.68
     weiße
    1.66
     ausein
    1.65
     mehrm
    1.62
     befes
    1.59
    Activations Density 0.004%

    No Known Activations