© 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. 34-GEMMASCOPE-RES-131K
    4. 86741
    Prev
    Next
    INDEX
    Explanations

    descriptions, names, and processes

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

    The neuron is keyed to temporal expressions and adverbs indicating timing (e.g. “soon,” “as soon as,” “from [time],” etc.).

    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
    మ్
    -0.86
     müssen
    -0.85
     rape
    -0.81
     benz
    -0.79
    shi
    -0.75
    sic
    -0.75
     Е
    -0.75
    urnum
    -0.75
    SR
    -0.74
     ben
    -0.73
    POSITIVE LOGITS
     Neop
    0.98
    皚
    0.95
     روزانه
    0.88
     Balth
    0.85
    trabaj
    0.81
    bruce
    0.81
    Sucursal
    0.80
    Sloth
    0.78
     spørsmål
    0.78
    Objetivos
    0.78
    Activations Density 0.007%

    No Known Activations