© 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. 22-GEMMASCOPE-RES-131K
    7. 129871
    Prev
    Next
    INDEX
    Explanations

    The neuron flags mentions of navigation or routing constructs in code (e.g. Intent, router/useHistory, navigation calls).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    navigation and state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    garh
    -0.98
     Adjustable
    -0.96
     Stadt
    -0.96
    enoch
    -0.96
    fattning
    -0.95
     adjustable
    -0.91
     Diarsipkan
    -0.90
     ruas
    -0.89
    TokenNameRPAREN
    -0.89
    шом
    -0.89
    POSITIVE LOGITS
    ренко
    1.05
     such
    0.92
     into
    0.91
    weisung
    0.88
    ouvrir
    0.86
     solchen
    0.83
    
    0.82
     Investigating
    0.82
     verur
    0.82
     interessanti
    0.81
    Activations Density 0.016%

    No Known Activations