© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20776
    Prev
    Next
    INDEX
    Explanations

    forced actions

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

    The neuron detects words expressing compulsion or coercion (e.g. “force,” “forced,” “forcing”).

    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
    ellemző
    -1.13
     suivantes
    -1.13
    jaus
    -1.08
     pintada
    -1.05
     szeret
    -1.05
    状況
    -1.05
     galore
    -1.03
    onucleotides
    -1.03
     linewidth
    -1.03
    ítu
    -1.03
    POSITIVE LOGITS
     by
    1.63
     about
    1.42
     for
    1.38
     their
    1.32
     forced
    1.30
     is
    1.27
     when
    1.25
     because
    1.23
     cuando
    1.11
     where
    1.08
    Activations Density 0.121%

    No Known Activations