© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39137
    Prev
    Next
    INDEX
    Explanations

    that followed by specific noun

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

    The neuron is essentially keyed to the token “creating.”

    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
     bidra
    -2.25
    ztes
    -2.11
    炱
    -2.11
     dokonce
    -2.11
    zten
    -2.05
    悧
    -1.98
     السياسية
    -1.97
     間取り
    -1.93
    酲
    -1.88
    ſchen
    -1.84
    POSITIVE LOGITS
    “
    2.48
    S
    2.13
    Y
    2.05
    ]
    1.98
     fateful
    1.98
    t
    1.97
    「
    1.88
    C
    1.82
    (!__
    1.81
    R
    1.80
    Activations Density 0.077%

    No Known Activations