© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67572
    Prev
    Next
    INDEX
    Explanations

    importance or relevance

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

    The neuron fires on occurrences of “matter(s)” used to express importance or relevance.

    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
     of
    -1.87
     autén
    -1.51
     {
    -1.39
    उत्तर
    -1.38
    ѝ
    -1.36
     esclavos
    -1.34
    isting
    -1.34
    袿
    -1.32
    смотря
    -1.30
     своем
    -1.30
    POSITIVE LOGITS
    </strong>
    1.83
     in
    1.48
     know
    1.46
     preciosa
    1.41
    toPromise
    1.38
     when
    1.37
     hermosa
    1.36
    会不会
    1.32
     predomin
    1.27
     mattered
    1.26
    Activations Density 0.012%

    No Known Activations