© 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. 26836
    Prev
    Next
    INDEX
    Explanations

    use and technology scenarios

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

    The neuron flags mentions of the actors or participants in a scenario (e.g. organizations, employees, and pronouns referring to them).

    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
     stolet
    -1.09
     budete
    -1.06
     people
    -1.03
     Simplemente
    -1.02
     Vergnügen
    -1.02
     there
    -1.01
    anggil
    -0.98
    ="";
    -0.96
     Ketika
    -0.95
     máte
    -0.95
    POSITIVE LOGITS
    使用
    1.29
     utiliser
    1.27
    use
    1.23
    用
    1.21
     استفاده
    1.16
     technolog
    1.13
     expliquer
    1.09
     Technology
    1.07
     use
    1.06
     hilfiger
    1.05
    Activations Density 0.177%

    No Known Activations