© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 44862
    Prev
    Next
    INDEX
    Explanations

    life, vida

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

    The neuron is detecting the Spanish word "vida" (meaning "life") in various contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    籏
    -2.41
    歘
    -2.41
    垍
    -2.36
    tedì
    -2.34
    er
    -2.34
    晢
    -2.33
    𓁹
    -2.31
     titled
    -2.27
     márm
    -2.23
    ◨
    -2.23
    POSITIVE LOGITS
     But
    2.81
     If
    2.53
     With
    2.47
    .
    2.38
    If
    2.38
     They
    2.33
     آنها
    2.28
    鸯
    2.25
     vida
    2.19
     From
    2.14
    Activations Density 0.001%

    No Known Activations