© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39909
    Prev
    Next
    INDEX
    Explanations

    movement and destination

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

    The neuron fires on passages describing movement or transport—i.e. verbs and related nouns about moving, shipping, or relocating equipment, goods, or vehicles and their sites.

    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
     
    -1.23
     both
    -1.22
    ↵
    -1.22
     zvíř
    -1.21
     BOTH
    -1.16
    ocusing
    -1.14
     řešení
    -1.10
    Démographie
    -1.09
    atively
    -1.07
     grafts
    -1.06
    POSITIVE LOGITS
     destined
    1.37
     Terrasse
    1.25
    верка
    1.20
     државе
    1.19
     terdekat
    1.18
     berikutnya
    1.16
     OGSÅ
    1.15
     its
    1.11
    回到了
    1.09
     storage
    1.07
    Activations Density 0.029%

    No Known Activations