© 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. 34-GEMMASCOPE-RES-131K
    7. 31022
    Prev
    Next
    INDEX
    Explanations

    different colors, styles, or types

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

    The neuron is activated by very common, high‐frequency function words (e.g. stop words like “the,” “and,” “you,” “to,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     capitol
    -1.13
     tupperware
    -1.10
     Ebay
    -1.09
     läßt
    -1.08
    Ebay
    -1.05
     attentions
    -1.03
    uitton
    -1.02
    isesti
    -1.02
    uchos
    -1.02
     muß
    -0.98
    POSITIVE LOGITS
     ‌
    1.34
     your
    1.24
     разных
    1.23
     shortlisted
    1.21
    NoOf
    1.20
    FAQs
    1.11
    <strong>
    1.10
     FAQs
    1.10
    ‌
    1.06
     مُ
    1.05
    Activations Density 0.066%

    No Known Activations