© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 45506
    Prev
    Next
    INDEX
    Explanations

    dash separators before names

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

    The neuron fires on horizontal separator lines made up of repeated dashes.

    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
     ajuta
    -1.01
    ここでは
    -0.98
     หร
    -0.93
    児島
    -0.91
     mater
    -0.90
    зы
    -0.88
     municipalité
    -0.88
     attorno
    -0.86
    美好的
    -0.85
     seem
    -0.84
    POSITIVE LOGITS
    snip
    1.58
    ˏ
    1.30
    ˋ
    1.23
    =-=-=-=-
    1.21
    oOo
    1.17
    叹息
    1.05
    𝕓
    1.03
     kalın
    1.02
    Campeonato
    1.01
     beslu
    0.99
    Activations Density 0.032%

    No Known Activations