© 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. 66551
    Prev
    Next
    INDEX
    Explanations

    toward / towards

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

    This neuron detects instances of the word “toward” (and its variant “towards”).

    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
    方針
    -2.78
    ですが
    -2.50
    
    -2.25
    結果は
    -2.20
     is
    -2.16
    などを
    -2.14
    详
    -2.09
    があります
    -2.09
    立場
    -2.08
    中でも
    -2.05
    POSITIVE LOGITS
     the
    2.69
    CHREIB
    2.38
     ſta
    2.34
    さぁ
    2.25
     Hacer
    2.25
     グッズ
    2.25
     Atención
    2.23
    鹀
    2.19
    卝
    2.17
    殽
    2.16
    Activations Density 0.009%

    No Known Activations