© 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. 111158
    Prev
    Next
    INDEX
    Explanations

    get me, discover myself

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

    The neuron fires on first-person statements, especially the pronoun “I” (and its equivalents) introducing personal actions or experiences.

    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
     themselves
    -2.14
     is
    -1.84
     münchen
    -1.82
     for
    -1.73
     birbir
    -1.71
     you
    -1.70
     another
    -1.59
    ,
    -1.55
    -
    -1.46
    –¿
    -1.45
    POSITIVE LOGITS
     myself
    2.27
    this
    1.69
    鹩
    1.62
     ***!
    1.58
    myself
    1.58
     this
    1.58
    stopper
    1.55
    igrette
    1.53
    ispiele
    1.52
    jusqu
    1.52
    Activations Density 5.108%

    No Known Activations