© 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. 39776
    Prev
    Next
    INDEX
    Explanations

    the word of

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

    This neuron fires on phrases that frame “the future of” a topic—that is, headings or mentions of “future of ….”

    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
     verschillen
    -1.76
     gouden
    -1.64
     natuurlijke
    -1.55
     ferdig
    -1.55
     they
    -1.53
     that
    -1.53
     illustratie
    -1.53
     hoogte
    -1.53
     smaak
    -1.52
     prachtige
    -1.50
    POSITIVE LOGITS
     of
    1.91
    ivamente
    1.44
     皇族
    1.44
     apparence
    1.39
    rógeno
    1.38
    mographie
    1.38
     satte
    1.38
    ż
    1.38
     idyl
    1.38
     notor
    1.37
    Activations Density 0.109%

    No Known Activations