© 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. 34-GEMMASCOPE-RES-131K
    7. 90417
    Prev
    Next
    INDEX
    Explanations

    road or path names

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

    The neuron strongly activates on passages formatted and phrased like biblical scripture verses.

    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
    HasAnnotation
    -0.79
    pushFollow
    -0.76
    辩
    -0.71
    쿼
    -0.71
    ThemeOverlay
    -0.71
     retraso
    -0.71
    cosas
    -0.70
    liver
    -0.70
    谩
    -0.70
    ags
    -0.69
    POSITIVE LOGITS
     narrow
    1.37
     path
    1.28
    narrow
    1.21
    Narrow
    1.16
     gate
    1.11
     paths
    1.09
     pathway
    1.05
     Narrow
    1.01
     strait
    0.98
     broad
    0.94
    Activations Density 0.007%

    No Known Activations