© 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. 60028
    Prev
    Next
    INDEX
    Explanations

    direction and movement

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

    The neuron detects adverbial particles or prepositional “particles” (up, down, off, on, out, again, forth, etc.) often used in phrasal 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_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
    recently
    -1.84
     beberapa
    -1.80
     trám
    -1.70
    などで
    -1.63
     kilka
    -1.63
     proporciona
    -1.63
    かっ
    -1.63
     jednej
    -1.61
     wielu
    -1.59
    often
    -1.59
    POSITIVE LOGITS
     on
    1.74
    hline
    1.59
     as
    1.59
     Ironically
    1.57
     Both
    1.55
    ,
    1.54
     Probably
    1.52
     extensive
    1.52
     Even
    1.49
     Perhaps
    1.49
    Activations Density 0.016%

    No Known Activations