© 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. 4190
    Prev
    Next
    INDEX
    Explanations

    noun followed by specific word

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

    The neuron fires strongly on capitalized proper names or titles (named entities).

    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
    豊かな
    -0.81
     semejante
    -0.77
     sabato
    -0.77
    Ꮩ
    -0.77
     Irm
    -0.76
     дитя
    -0.75
     reliant
    -0.75
    悽
    -0.75
     sebelah
    -0.75
    tts
    -0.74
    POSITIVE LOGITS
    kit
    1.34
    star
    1.23
    heart
    1.15
    paw
    1.07
    Kit
    0.90
    Star
    0.88
    flight
    0.88
    tail
    0.85
     heart
    0.83
    pool
    0.82
    Activations Density 0.024%

    No Known Activations