© 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. 13547
    Prev
    Next
    INDEX
    Explanations

    media topics discussed positively

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

    This neuron activates on salient content words—especially domain-specific nouns and key topic terms—rather than on common function words.

    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
     for
    -1.13
     at
    -1.05
     before
    -1.04
    ､
    -1.04
     with
    -1.02
     several
    -1.02
    〈
    -1.02
     dür
    -0.99
     Because
    -0.99
     this
    -0.98
    POSITIVE LOGITS
     astounding
    1.19
     '',
    1.16
     amazing
    1.15
     ausgewählt
    1.13
     Verfasser
    1.09
     alluring
    1.08
    mostly
    1.07
     exceptional
    1.07
    phylaxis
    1.07
     conscientes
    1.05
    Activations Density 0.011%

    No Known Activations