© 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. 10-GEMMASCOPE-RES-131K
    7. 57449
    Prev
    Next
    INDEX
    Explanations

    about what is next

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

    The neuron detects enthusiasm or positive appraisal words—terms conveying excitement, motivation, or favorable evaluation.

    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
    tuigen
    -1.34
     ormai
    -1.33
     аналоги
    -1.27
     inmiddels
    -1.27
     они
    -1.27
    他们
    -1.25
    </tfoot>
    -1.25
    条件
    -1.23
     gesprochen
    -1.20
    They
    -1.19
    POSITIVE LOGITS
    nological
    1.35
    みたら
    1.14
     where
    1.14
    ville
    1.08
     itself
    1.07
    ござい
    1.07
     esportivo
    1.06
    posit
    1.05
    yyy
    1.05
     औसत
    1.03
    Activations Density 0.053%

    No Known Activations