© 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. 10-GEMMASCOPE-RES-131K
    4. 8284
    Prev
    Next
    INDEX
    Explanations

    comparative comparative more than

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

    The neuron fires on comparative‐degree constructions—particularly instances of “more” (often in “any more,” “no more,” or “more … than”) and similar comparative words.

    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
    </b>
    -1.49
     and
    -1.36
     T
    -1.24
     so
    -1.21
     THE
    -1.13
    riert
    -1.09
    ulus
    -1.06
    andt
    -1.05
    lang
    -1.03
    </strong>
    -1.01
    POSITIVE LOGITS
    folgung
    1.21
     oock
    1.20
     kopen
    1.20
     jurk
    1.20
     staffel
    1.17
    edakan
    1.14
    idance
    1.13
     prenn
    1.12
     olie
    1.11
     vernis
    1.11
    Activations Density 0.057%

    No Known Activations