© 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. 71996
    Prev
    Next
    INDEX
    Explanations

    similar meaning words

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

    The neuron is flagging ordinary words in the main body text of prose (as opposed to navigation links, code snippets, or other boilerplate).

    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
    mə
    -1.02
    𝗉
    -0.93
     mucha
    -0.89
     konkrét
    -0.89
     perió
    -0.86
    hosa
    -0.86
     anum
    -0.84
     muchas
    -0.84
     enfri
    -0.83
    Notable
    -0.83
    POSITIVE LOGITS
     ebenfalls
    3.25
     тоже
    2.89
     also
    2.42
     również
    2.31
    こちらも
    2.17
     another
    2.14
    同样
    2.11
     similarly
    2.05
     equally
    2.02
     szint
    2.02
    Activations Density 0.071%

    No Known Activations