© 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. 10-GEMMASCOPE-RES-131K
    7. 60244
    Prev
    Next
    INDEX
    Explanations

    hierarchical structures

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

    The neuron activates on occurrences of the root “hierarch” (e.g. in words like hierarchical, hierarchy, hierarchies).

    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
    ↵↵
    -3.84
     “
    -2.30
    ↵
    -2.20
     jsou
    -2.17
    irical
    -2.16
    珝
    -2.08
     Zweiten
    -2.08
     akin
    -2.06
    ’,
    -2.03
     cuya
    -2.03
    POSITIVE LOGITS
     are
    2.63
    みると
    2.44
    みたら
    2.41
    蠵
    2.34
    la
    2.33
    硨
    2.27
    一旁的
    2.27
    </strong>
    2.19
    of
    2.16
     '
    2.14
    Activations Density 0.002%

    No Known Activations