© 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. 34-GEMMASCOPE-RES-131K
    7. 66288
    Prev
    Next
    INDEX
    Explanations

    self-reference or personal statements

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     our
    -2.25
     μας
    -1.63
     we
    -1.55
     us
    -1.54
    我們
    -1.51
    给我们
    -1.50
     his
    -1.46
    我们
    -1.45
     yourself
    -1.31
    讓我們
    -1.31
    POSITIVE LOGITS
     myself
    2.33
    myself
    2.06
     my
    1.51
     Myself
    1.30
     خودم
    1.30
    我自己
    1.29
    Myself
    1.10
    KJV
    1.07
     mereka
    0.99
     хочу
    0.98
    Activations Density 0.067%

    No Known Activations