© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 45456
    Prev
    Next
    INDEX
    Explanations

    Parse Realm engine data

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

    This neuron fires on mentions of specific data‐oriented SDKs/frameworks (e.g. “Realm,” “Parse,” “PFQuery,” etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     chico
    -1.57
    
    -1.53
     cortado
    -1.45
     not
    -1.43
     segar
    -1.42
    ны
    -1.41
     Zuid
    -1.39
    før
    -1.39
     Desember
    -1.39
     acum
    -1.39
    POSITIVE LOGITS
     идеально
    1.63
    <td>
    1.48
     jedną
    1.27
    これに
    1.27
     дов
    1.25
     Gave
    1.23
     tačiau
    1.20
     Ruling
    1.20
     Totally
    1.19
     około
    1.18
    Activations Density 0.043%

    No Known Activations