© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111878
    Prev
    Next
    INDEX
    Explanations

    sequential actions after 'then'

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

    words that indicate a transition to the next step or action in instructional or procedural text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     a
    -2.44
     todėl
    -1.66
     they
    -1.62
     debía
    -1.61
     indivíduo
    -1.53
     certain
    -1.53
    midler
    -1.50
     desejo
    -1.48
     bahkan
    -1.48
     tikra
    -1.47
    POSITIVE LOGITS
     your
    2.11
     or
    1.88
     and
    1.58
     yourself
    1.57
    corbic
    1.55
     駅前
    1.53
     find
    1.49
    ynchronous
    1.46
    ympto
    1.45
    your
    1.44
    Activations Density 0.017%

    No Known Activations