© 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. 35374
    Prev
    Next
    INDEX
    Explanations

    data delimiters | , - _

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

    This neuron activates on numeric coordinates in circuit‐diagram tuples (i.e. the numbers inside the parentheses specifying wire or component positions).

    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
    lenme
    -1.19
     escritores
    -1.16
     sentimos
    -1.16
     imprimi
    -1.15
    帼
    -1.14
    Groet
    -1.10
     its
    -1.09
    icula
    -1.08
     takı
    -1.08
     vannak
    -1.08
    POSITIVE LOGITS
    y
    1.16
    He
    1.11
    in
    1.07
    un
    1.05
    and
    1.02
    at
    1.02
     weder
    1.02
     geograf
    1.01
     also
    1.01
    on
    1.01
    Activations Density 0.004%

    No Known Activations