© 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. 22-GEMMASCOPE-RES-131K
    7. 25545
    Prev
    Next
    INDEX
    Explanations

    stopping actions

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

    The neuron strongly activates on verbs that express stopping, quitting, removing, or otherwise ceasing something.

    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
    これは
    -0.92
     использование
    -0.84
    Via
    -0.83
    TIF
    -0.82
     használ
    -0.81
    versiti
    -0.81
     otros
    -0.81
    楽しく
    -0.81
    文分享
    -0.80
     Algunos
    -0.79
    POSITIVE LOGITS
     its
    1.22
     this
    0.98
     people
    0.94
     atau
    0.91
     our
    0.91
     gdyż
    0.90
    ったり
    0.90
     their
    0.87
     esprit
    0.85
     hoặc
    0.85
    Activations Density 0.039%

    No Known Activations