© 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. 22-GEMMASCOPE-RES-131K
    7. 93111
    Prev
    Next
    INDEX
    Explanations

    itself, himself, themselves

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

    The neuron picks out the single most salient content word in a sentence—typically the key noun or adjective that signals the main topic or emphasis of that text.

    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
    toma
    -0.93
    muli
    -0.93
    kiat
    -0.92
     अगर
    -0.92
    cessite
    -0.89
    bila
    -0.87
    DIG
    -0.86
     если
    -0.85
    ₿
    -0.84
     exaggeration
    -0.83
    POSITIVE LOGITS
     itself
    1.43
     justement
    1.29
    indeed
    1.26
     himself
    1.16
     selve
    1.15
    namely
    1.08
     themselves
    1.08
     indeed
    1.04
    自ら
    1.03
    Indeed
    1.02
    Activations Density 0.080%

    No Known Activations