© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 13384
    Prev
    Next
    INDEX
    Explanations

    conditional outcomes

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

    The neuron is highly sensitive to passive‐voice constructions (e.g. occurrences of auxiliary “be” or modals plus a past participle).

    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
     Somehow
    -0.96
    От
    -0.82
    成田
    -0.81
    の様子
    -0.80
    新型コロナ
    -0.79
    Aplikasi
    -0.79
    今朝
    -0.79
    Ча
    -0.78
     izquier
    -0.78
    ꙑ
    -0.77
    POSITIVE LOGITS
     therefore
    1.27
    にとっては
    1.02
     current
    0.98
     most
    0.95
     thus
    0.94
     puisque
    0.94
     majority
    0.90
    吁
    0.90
     praticamente
    0.90
    ∴
    0.88
    Activations Density 0.094%

    No Known Activations