© 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. 10-GEMMASCOPE-RES-131K
    7. 22432
    Prev
    Next
    INDEX
    Explanations

    most common

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

    The neuron detects superlative degree expressions—phrases that emphasize the “most” or “best” of something.

    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
     especially
    -1.51
     your
    -1.42
     also
    -1.41
     gese
    -1.38
     vooral
    -1.38
     lainnya
    -1.30
     gewor
    -1.29
    ").
    -1.24
     fiatal
    -1.23
     egyéb
    -1.20
    POSITIVE LOGITS
    Até
    1.21
     polie
    1.16
    шены
    1.15
     manipula
    1.15
     aproximativ
    1.13
     miniatur
    1.13
     indestru
    1.11
     one
    1.10
     traged
    1.09
     abusi
    1.09
    Activations Density 0.167%

    No Known Activations