© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66886
    Prev
    Next
    INDEX
    Explanations

    I find myself

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

    The neuron activates on the verb “find” (especially in “I find …”) marking personal judgments 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_22/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
     which
    -1.30
     what
    -1.30
     just
    -1.22
     a
    -1.19
     know
    -1.16
     undoubtedly
    -1.15
     five
    -1.14
     efficiently
    -1.13
     definitely
    -1.13
     approximately
    -1.12
    POSITIVE LOGITS
     it
    1.79
     tecnológicos
    1.30
     gebra
    1.30
     electrónicos
    1.26
    ふた
    1.25
     BEING
    1.23
    自己在
    1.22
     potrebné
    1.22
     básicos
    1.20
     spørsmål
    1.20
    Activations Density 0.018%

    No Known Activations