© 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. 60895
    Prev
    Next
    INDEX
    Explanations

    what / whatever / wherever

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

    The neuron is responding to open‐ended “wh-” words and their “-ever” variants (e.g. what, whatever, whenever, wherever).

    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
     mesma
    -1.61
     wszystkie
    -1.55
    𖣔
    -1.52
     vendar
    -1.51
     nuovo
    -1.47
     Schluß
    -1.46
     delincuentes
    -1.46
     ludicrous
    -1.42
     comanda
    -1.42
    込んで
    -1.40
    POSITIVE LOGITS
    0
    1.53
     else
    1.48
    ?
    1.45
     (\%)
    1.38
    soever
    1.38
    вання
    1.31
    eynman
    1.31
     gehabt
    1.30
     when
    1.30
     abbiano
    1.30
    Activations Density 0.038%

    No Known Activations