© 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. 18957
    Prev
    Next
    INDEX
    Explanations

    могут быть, por, видео, сохранить

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

    The neuron responds to personal‐agent words—that is, subject pronouns (I, you, we, они, вы, etc.) and their associated conjugated verb forms across different languages.

    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
     dichas
    -2.11
     ciertos
    -1.88
     dichos
    -1.67
     cuándo
    -1.55
     ciertas
    -1.48
    ための
    -1.44
    село
    -1.41
    Appellee
    -1.39
     herhangi
    -1.37
     imprescindible
    -1.37
    POSITIVE LOGITS
     our
    1.88
    S
    1.69
    A
    1.55
    O
    1.46
    of
    1.46
    el
    1.42
     köp
    1.41
     豐
    1.38
     inspiradoras
    1.38
    ,
    1.38
    Activations Density 0.020%

    No Known Activations