© 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. 68538
    Prev
    Next
    INDEX
    Explanations

    Valerie Bertinelli

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

    This neuron is effectively dormant—it doesn’t reliably activate on any tokens.

    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
     когато
    -1.19
     Acerca
    -1.12
     живе
    -1.07
    soit
    -1.06
     traitements
    -1.05
    oare
    -1.05
     Número
    -1.03
    取决
    -1.02
     дуже
    -1.02
     сьогодні
    -1.02
    POSITIVE LOGITS
    ">
    1.32
     also
    1.27
    "]
    1.15
     спор
    1.06
     reached
    1.06
     is
    1.02
     angrily
    0.98
     additionally
    0.97
    ..."
    0.96
    itis
    0.96
    Activations Density 0.006%

    No Known Activations