© 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. 73708
    Prev
    Next
    INDEX
    Explanations

    Q: Comparison Down eSource

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

    This neuron is effectively dead—it never activates on any token.

    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
     its
    -1.23
     get
    -1.00
     После
    -0.90
     pagkak
    -0.88
     query
    -0.88
     predict
    -0.88
    覚悟
    -0.85
     predic
    -0.84
    conditionally
    -0.84
     Robert
    -0.82
    POSITIVE LOGITS
     Spisak
    1.51
    université
    1.13
     mâle
    1.11
     нашим
    1.07
     །
    1.02
    uktion
    1.02
    vonne
    1.02
     Ekim
    1.01
    Diret
    1.01
     électro
    1.00
    Activations Density 0.000%

    No Known Activations