© 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. 11330
    Prev
    Next
    INDEX
    Explanations

    objects for play

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

    The neuron fires strongly on words naming toys and stuffed animals.

    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
    ↵
    -2.16
     aku
    -1.38
    </sup>
    -1.34
    le
    -1.33
     Even
    -1.30
    p
    -1.30
     between
    -1.30
     there
    -1.29
     vasi
    -1.26
     Not
    -1.24
    POSITIVE LOGITS
     suscep
    1.58
    SQUARE
    1.50
     všetky
    1.49
     wszystkie
    1.45
     投稿
    1.42
     affor
    1.41
     scavenging
    1.41
    espé
    1.40
    FormBuilder
    1.40
     strick
    1.40
    Activations Density 0.027%

    No Known Activations