© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59135
    Prev
    Next
    INDEX
    Explanations

    first person statements

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

    The neuron primarily detects the first‐person pronoun “I” (i.e., self‐references).

    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
    h
    -3.45
    c
    -3.39
    an
    -3.38
    n
    -3.31
    al
    -3.27
    m
    -3.20
    p
    -3.09
    b
    -3.02
    r
    -3.02
    s
    -2.95
    POSITIVE LOGITS
    蚍
    2.70
    
    2.52
    蓠
    2.50
    をよく
    2.47
    骉
    2.47
    
    2.33
     LIKE
    2.28
    を書く
    2.25
    肏
    2.25
    雠
    2.23
    Activations Density 0.274%

    No Known Activations