© 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. 66476
    Prev
    Next
    INDEX
    Explanations

    forced into action

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

    The neuron activates on occurrences of “force” and its inflected forms (forces, forced, forcing) in text.

    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
    szám
    -1.05
     szeret
    -0.98
     föres
    -0.96
     sàng
    -0.96
    ньому
    -0.96
    ٫
    -0.95
     there
    -0.95
    acity
    -0.94
     támogat
    -0.94
    кра
    -0.91
    POSITIVE LOGITS
     forced
    1.52
    forced
    1.26
     Forced
    1.20
     into
    1.17
    Forced
    1.12
     to
    1.06
     обов
    1.05
    Either
    0.96
    must
    0.93
     حتما
    0.93
    Activations Density 0.047%

    No Known Activations