© 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. 68554
    Prev
    Next
    INDEX
    Explanations

    handling your data or orders

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

    The neuron spots -ing forms (gerunds) that name administrative or procedural actions (e.g. processing, reviewing, storing).

    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
    -1.16
     A
    -1.09
     should
    -1.09
     T
    -1.07
    :
    -1.05
     Both
    -1.04
    T
    -1.03
     k
    -1.02
    t
    -1.00
     In
    -1.00
    POSITIVE LOGITS
     you
    1.70
     everyone
    1.66
     anyone
    1.46
     konkrét
    1.41
     verhind
    1.34
     personnaliser
    1.27
     vám
    1.27
     enfermera
    1.26
     každého
    1.24
     vaše
    1.23
    Activations Density 0.083%

    No Known Activations