© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 14708
    Prev
    Next
    INDEX
    Explanations

    multilingual text and phrases

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

    The neuron flags the inclusive, community-oriented language of “you,” “we,” “together,” “place,” “where,” etc., as it appears in mission-statement or invitation-style passages.

    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
     or
    -2.39
     плохо
    -1.49
     или
    -1.46
    новые
    -1.36
    But
    -1.34
     menghubungi
    -1.33
     on
    -1.32
     üblichen
    -1.31
     समस्या
    -1.31
     khawatir
    -1.31
    POSITIVE LOGITS
     escaleras
    1.80
     perigo
    1.77
     estranho
    1.69
     traseira
    1.59
     sujeito
    1.56
     cancelamento
    1.54
     města
    1.53
     sustancias
    1.51
    汌
    1.50
     doubtless
    1.47
    Activations Density 0.049%

    No Known Activations