© 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. 44537
    Prev
    Next
    INDEX
    Explanations

    born, pillar, stage, analyst

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

    The neuron fires on capitalized mid-sentence words—i.e. proper names, brands, titles, or other named entities.

    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
    tanto
    -1.49
    especially
    -1.41
     such
    -1.41
    such
    -1.39
     especially
    -1.39
     particularly
    -1.35
    particularly
    -1.32
     their
    -1.30
     they
    -1.30
     when
    -1.23
    POSITIVE LOGITS
     has
    1.48
    isait
    1.48
    écuter
    1.48
     "..\..\..\
    1.43
     или
    1.39
     cyclisme
    1.37
     magasin
    1.34
     valeur
    1.33
    ÉS
    1.32
    人は
    1.31
    Activations Density 0.155%

    No Known Activations