© 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. 39868
    Prev
    Next
    INDEX
    Explanations

    nonprofit, private, academic, source

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

    This neuron spotlights hyphenated or compound descriptors (e.g. “not-for-profit,” “open-source,” “peer-reviewed,” “cloud-based,” “faith-based,” “private,” “quarterly”) that classify organizations, projects, or publications.

    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
     more
    -1.70
     potrzebu
    -1.57
     things
    -1.55
     mało
    -1.55
     because
    -1.53
     dlaczego
    -1.52
     chcą
    -1.52
     various
    -1.52
     numerous
    -1.45
     insisting
    -1.45
    POSITIVE LOGITS
     rapor
    1.62
     brune
    1.56
     ſou
    1.55
     filtres
    1.52
     and
    1.50
     skr
    1.50
     stres
    1.49
     benzin
    1.48
     pelu
    1.47
     forment
    1.47
    Activations Density 0.492%

    No Known Activations