© 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. 34-GEMMASCOPE-RES-131K
    7. 31078
    Prev
    Next
    INDEX
    Explanations

    worthy of

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

    The neuron activates on tokens containing the root “worth” (e.g. worthy, worthiness, WORTH).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     рады
    -0.89
     width
    -0.89
    ungkin
    -0.84
     well
    -0.83
     ז
    -0.82
     onda
    -0.81
    王朝
    -0.81
    aughey
    -0.80
     unwarranted
    -0.80
     warranty
    -0.79
    POSITIVE LOGITS
    iness
    1.70
     mentioning
    1.38
    INESS
    1.24
     of
    1.13
     Mention
    1.07
     mention
    1.05
    mention
    1.04
     adversaries
    1.01
     adversary
    1.01
    iest
    1.00
    Activations Density 0.009%

    No Known Activations