© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 15058
    Prev
    Next
    INDEX
    Explanations

    economic effort and results

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

    The neuron strongly activates on the preposition “of,” especially when it links two nouns in noun-of-noun phrases.

    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
     سينما
    -1.30
    וּ
    -1.29
     бампер
    -1.28
     περ
    -1.27
    楽しめる
    -1.26
     onOptions
    -1.23
     isolato
    -1.23
     komplet
    -1.21
    +}\
    -1.18
     "}";
    -1.17
    POSITIVE LOGITS
     what
    1.60
     for
    1.40
     economic
    1.32
     our
    1.28
     berbagai
    1.27
     production
    1.24
     ilustrasi
    1.20
    乃是
    1.20
    ospital
    1.18
     السياس
    1.17
    Activations Density 0.015%

    No Known Activations