© 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. 36254
    Prev
    Next
    INDEX
    Explanations

    discovery, event, or outcome

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

    The neuron strongly activates on past-tense action verbs.

    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
     these
    -1.66
     boute
    -1.25
     apartament
    -1.23
    骉
    -1.19
    umers
    -1.19
     què
    -1.17
     wyn
    -1.16
     luka
    -1.15
     uda
    -1.14
     alip
    -1.13
    POSITIVE LOGITS
     another
    1.65
    Another
    1.56
     one
    1.30
     semejante
    1.28
    Perhaps
    1.20
     first
    1.20
    Otra
    1.13
    Spinach
    1.10
     two
    1.10
    Приготовление
    1.08
    Activations Density 0.065%

    No Known Activations