© 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. 22-GEMMASCOPE-RES-131K
    7. 39300
    Prev
    Next
    INDEX
    Explanations

    shell redirection or related technical terms

    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
    Bisous
    -0.92
    Bises
    -0.90
     argumenta
    -0.87
    attamento
    -0.85
     Penh
    -0.85
     correspondant
    -0.82
     spannende
    -0.80
     counterpart
    -0.79
    setLayoutManager
    -0.79
    ված
    -0.78
    POSITIVE LOGITS
     first
    1.06
     directly
    1.05
     between
    0.94
     relations
    0.92
     interactions
    0.89
     intermediate
    0.89
     pairwise
    0.88
     third
    0.87
     první
    0.84
     intermediary
    0.81
    Activations Density 0.117%

    No Known Activations