© 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. 10326
    Prev
    Next
    INDEX
    Explanations

    stormstormingstormy weather

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

    The neuron activates on words containing the character sequence “stor,” in particular at the start of words (e.g. storm, stories, Stormcloaks).

    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
    ?...
    -2.28
    0
    -2.27
    ?!?
    -2.22
    饪
    -2.19
     \&
    -2.19
     hård
    -2.17
    полне
    -2.14
    .~(\
    -2.13
     Himo
    -2.09
    饞
    -2.09
    POSITIVE LOGITS
     speci
    2.50
    y
    2.22
     verkau
    2.13
    亹
    2.06
     nimble
    2.05
    情况下
    1.99
     Stoffe
    1.99
    奩
    1.97
    仵
    1.96
     fünf
    1.88
    Activations Density 0.009%

    No Known Activations