© 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. 6970
    Prev
    Next
    INDEX
    Explanations

    stumbled upon

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

    The neuron activates on dynamic action verbs.

    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
     secciones
    -0.88
     how
    -0.82
    💴
    -0.81
     prosegu
    -0.80
    Kes
    -0.79
     barrera
    -0.79
     migliore
    -0.78
     Elevation
    -0.76
     牛肉
    -0.76
     getting
    -0.75
    POSITIVE LOGITS
     into
    0.96
    tize
    0.93
     hanged
    0.92
     nationale
    0.87
     railroads
    0.86
    бата
    0.85
     unto
    0.84
    €”
    0.84
    эй
    0.84
     furthermore
    0.84
    Activations Density 0.077%

    No Known Activations