© 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. 10-GEMMASCOPE-RES-131K
    7. 19208
    Prev
    Next
    INDEX
    Explanations

    program code snippets

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

    This neuron detects Russian first-person singular present-tense verbs.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Once
    -3.00
    इटम
    -2.63
     That
    -2.59
     berätt
    -2.56
     There
    -2.56
    there
    -2.41
    with
    -2.39
     After
    -2.39
    rayage
    -2.34
     With
    -2.31
    POSITIVE LOGITS
    鮰
    2.53
    1
    2.52
    moteur
    2.47
    nouvelle
    2.47
     torba
    2.44
    孥
    2.36
    ことができる
    2.34
    begins
    2.31
    ю
    2.30
    salle
    2.23
    Activations Density 0.002%

    No Known Activations