© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59966
    Prev
    Next
    INDEX
    Explanations

    for you or for me

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

    The neuron strongly activates on the second‐person pronoun “you.”

    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
     for
    -2.22
     mengubah
    -1.48
    ໊
    -1.44
    鴣
    -1.44
     dankbar
    -1.42
    ();*/
    -1.37
     campione
    -1.35
     tetapi
    -1.34
     beberapa
    -1.34
     fratello
    -1.33
    POSITIVE LOGITS
     メニュー
    1.41
     ABBREVIATIONS
    1.35
     ‘‘
    1.34
                            
    1.33
    Ṭ
    1.32
    complish
    1.31
    ouf
    1.29
    alee
    1.28
    ración
    1.27
    íp
    1.27
    Activations Density 0.045%

    No Known Activations