© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99190
    Prev
    Next
    INDEX
    Explanations

    need for or need to

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

    The neuron flags any occurrence of the token “need” (or tokens containing the substring “need”).

    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
    鯓
    -2.67
    喾
    -2.58
    珢
    -2.42
     появляется
    -2.41
    irected
    -2.39
    داية
    -2.36
    鱻
    -2.36
     землю
    -2.34
    韫
    -2.33
    秝
    -2.33
    POSITIVE LOGITS
     However
    3.09
     The
    2.86
     It
    2.83
     Whether
    2.61
     Therefore
    2.50
    鵟
    2.41
     wuß
    2.39
     Until
    2.38
    
    2.36
    であった
    2.30
    Activations Density 0.066%

    No Known Activations