© 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. 10-GEMMASCOPE-RES-131K
    7. 85176
    Prev
    Next
    INDEX
    Explanations

    absence of movement

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

    The main thing this neuron does is detect occurrences of the verb “move” (in any form).

    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
     expliquer
    -1.65
    0
    -1.45
    ënten
    -1.45
     بداية
    -1.45
    rät
    -1.41
    のみ
    -1.38
    的に
    -1.34
     réunions
    -1.33
    ﹍﹍
    -1.32
    ཿ
    -1.32
    POSITIVE LOGITS
     verbindet
    1.47
     جيد
    1.42
     detects
    1.41
     behaves
    1.40
     exorbitant
    1.37
     from
    1.36
     their
    1.35
     six
    1.34
     at
    1.33
     executes
    1.32
    Activations Density 0.016%

    No Known Activations