© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 22243
    Prev
    Next
    INDEX
    Explanations

    now and present state

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

    This neuron detects first‐person expressions of personal experience or emotional states, marked by “me” or “I” together with a verb (e.g. “gives me,” “feel energized,” “is supposed to be”).

    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
     originally
    -1.88
     yesterday
    -1.50
    ților
    -1.48
    :
    -1.44
     նաև
    -1.39
    cím
    -1.38
     previously
    -1.38
     of
    -1.36
    OTION
    -1.34
     formerly
    -1.32
    POSITIVE LOGITS
     now
    1.87
    ↵↵
    1.75
    现在的
    1.43
    Deine
    1.25
    now
    1.23
    如今
    1.23
    carus
    1.22
     ');
    1.21
    Сейчас
    1.19
     ");
    1.18
    Activations Density 2.490%

    No Known Activations