© 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. 34-GEMMASCOPE-RES-131K
    7. 108815
    Prev
    Next
    INDEX
    Explanations

    Rights Reserved

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

    The neuron fires on dotted “path‐like” sequences—anything using repeated “.” (and accompanying “/”) such as URLs, package names, or method calls.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Windsor
    -0.68
    inent
    -0.68
    hita
    -0.66
    qui
    -0.65
    phytes
    -0.64
    Neue
    -0.62
    匚
    -0.61
     届
    -0.60
    hich
    -0.60
     equipment
    -0.60
    POSITIVE LOGITS
    FieldValue
    0.75
     物語
    0.73
    iería
    0.72
     meiosis
    0.72
    getLatitude
    0.71
     Fus
    0.67
     Saito
    0.67
    Etat
    0.67
     lezen
    0.67
    باب
    0.67
    Activations Density 0.051%

    No Known Activations