© 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. 27874
    Prev
    Next
    INDEX
    Explanations

    even or emphasis

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

    The neuron flags text describing the attribution of life or sentience to inanimate things.

    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
     similarly
    -1.16
     either
    -0.97
    similar
    -0.95
    either
    -0.92
     similar
    -0.88
     либо
    -0.86
     entweder
    -0.85
    Either
    -0.84
     followed
    -0.83
     exactly
    -0.82
    POSITIVE LOGITS
     even
    2.78
     даже
    2.53
     навіть
    2.50
     sogar
    2.38
     incluso
    2.31
     bahkan
    2.22
     حتی
    2.08
     jopa
    2.08
     zelfs
    2.06
     nawet
    1.92
    Activations Density 0.098%

    No Known Activations