© 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. 22-GEMMASCOPE-RES-131K
    7. 73368
    Prev
    Next
    INDEX
    Explanations

    devices and hardware

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

    The neuron fires on tokens denoting model numbers, version identifiers, or generation labels (i.e. numeric references in product names or software versions).

    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
     Pfar
    -1.23
    「
    -1.23
     plena
    -1.20
    出一
    -1.16
    ByVersion
    -1.15
     week
    -1.13
    queryInterface
    -1.13
     laws
    -1.11
     food
    -1.11
     items
    -1.08
    POSITIVE LOGITS
     deviennent
    1.35
     actualización
    1.35
     作り方
    1.34
    惴
    1.34
     triomphe
    1.32
     semoga
    1.31
     célè
    1.29
    謚
    1.26
    anything
    1.23
    鸸
    1.23
    Activations Density 0.054%

    No Known Activations