© 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. 10-GEMMASCOPE-RES-131K
    7. 112909
    Prev
    Next
    INDEX
    Explanations

    memory efficiency and usage

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

    technical discussions about memory usage and computational efficiency in programming contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    the neuron activates on technical mentions of memory usage or memory‐related terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    来越
    -1.17
     civilización
    -1.15
     świata
    -1.14
     audiencia
    -1.13
    mybatisplus
    -1.12
     reunión
    -1.10
     brauch
    -1.09
     polémica
    -1.07
    imantan
    -1.05
     for
    -1.04
    POSITIVE LOGITS
    Kiedy
    1.23
    från
    1.19
     grosse
    1.16
    When
    1.13
    inaison
    1.12
    Ketika
    1.12
    咱们
    1.10
    Gdzie
    1.10
    Current
    1.09
    tosí
    1.09
    Activations Density 0.147%

    No Known Activations