© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108088
    Prev
    Next
    INDEX
    Explanations

    estar conjugations

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

    The neuron fires on Spanish present‐tense conjugations of the verb “estar” (e.g. está, estamos, están, estoy).

    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
     capaz
    -1.12
    Longueur
    -1.10
     not
    -1.09
    шайте
    -1.03
    archical
    -0.98
    tismo
    -0.98
    unyai
    -0.98
     laajenta
    -0.97
    それが
    -0.95
     that
    -0.94
    POSITIVE LOGITS
     in
    1.14
     avail
    0.89
     Stateless
    0.84
     carbur
    0.79
     serp
    0.77
     involved
    0.77
     available
    0.77
    んですね
    0.77
     Athen
    0.77
    ct
    0.77
    Activations Density 0.008%

    No Known Activations