© 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. 22-GEMMASCOPE-RES-131K
    7. 72164
    Prev
    Next
    INDEX
    Explanations

    media and events

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

    This neuron spots the document’s central topical noun—that is, the main subject word (e.g. “survey,” “shower,” “film,” “article”) that indicates the focus of a section.

    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
     or
    -1.27
     things
    -0.91
    六年
    -0.90
     B
    -0.89
    Given
    -0.88
    ૫
    -0.88
     miesię
    -0.87
    自从
    -0.86
     идут
    -0.84
     L
    -0.84
    POSITIVE LOGITS
     salari
    1.13
     serre
    1.09
     veu
    1.08
     kere
    1.05
     ihan
    1.04
     pandemi
    1.04
     pince
    1.04
     levé
    1.03
     registre
    1.03
     fré
    1.03
    Activations Density 0.057%

    No Known Activations