© 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. 39968
    Prev
    Next
    INDEX
    Explanations

    forced to

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

    The neuron is highly sensitive to the word “forced” (especially in “forced to”) indicating compulsion.

    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
     a
    -1.97
     they
    -1.84
     There
    -1.76
    اكل
    -1.70
     until
    -1.63
     could
    -1.52
     did
    -1.51
     suitable
    -1.51
     using
    -1.48
     During
    -1.48
    POSITIVE LOGITS
     spektak
    1.74
     konkret
    1.73
     étan
    1.73
    ↵
    1.70
    sometimes
    1.64
     kompak
    1.63
     historische
    1.58
    recently
    1.55
     komfor
    1.55
    lokal
    1.53
    Activations Density 0.016%

    No Known Activations