© 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. 22-GEMMASCOPE-RES-131K
    7. 38764
    Prev
    Next
    INDEX
    Explanations

    mathematical variable assignments

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

    This neuron never activates on any of these inputs—it appears to be effectively “dead” and doesn’t detect any pattern.

    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
     then
    -1.20
     persino
    -1.07
     svilupp
    -1.06
     addirittura
    -1.05
     firstly
    -1.03
     griechischen
    -1.02
     elección
    -1.00
     erwähnt
    -1.00
     rozwoju
    -0.98
     diferentes
    -0.97
    POSITIVE LOGITS
    慙
    1.32
     berle
    1.29
     certificat
    1.20
     flore
    1.17
    ♪♪
    1.16
    >@
    1.14
     berger
    1.13
     spion
    1.13
     perle
    1.12
     maniere
    1.12
    Activations Density 0.022%

    No Known Activations