© 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. 34-GEMMASCOPE-RES-131K
    7. 63236
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs

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

    The neuron fires on Czech/Slovak inflected word endings (i.e. case-marking suffixes with diacritics).

    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
     invited
    -1.06
     canopy
    -0.85
     received
    -0.75
     CRITERIA
    -0.71
    amas
    -0.70
     stwier
    -0.69
     follow
    -0.69
     aiuta
    -0.69
     aider
    -0.69
     hone
    -0.68
    POSITIVE LOGITS
     вну
    0.95
    Medi
    0.90
    鄞
    0.82
     communicating
    0.81
     concedes
    0.79
     ganó
    0.78
     prouver
    0.78
     breathes
    0.77
     EDI
    0.77
     препо
    0.76
    Activations Density 0.011%

    No Known Activations