© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6718
    Prev
    Next
    INDEX
    Explanations

    glory and honor

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

    The neuron lights up on words that introduce or occur in purpose/intent clauses—e.g. infinitive “to …” or “for …” phrases describing why something is done.

    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
    }=(\
    -0.72
    рис
    -0.71
     Jens
    -0.71
    intosh
    -0.70
    othea
    -0.69
     Permalink
    -0.69
     conserv
    -0.68
    andoah
    -0.68
    сми
    -0.68
     ficha
    -0.67
    POSITIVE LOGITS
     glorify
    2.88
     glor
    2.48
     honour
    2.47
    glor
    2.33
     glory
    2.31
     Glor
    2.31
     honor
    2.27
     glorified
    2.22
     Glory
    2.02
     Honour
    1.93
    Activations Density 0.023%

    No Known Activations