© 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. 81378
    Prev
    Next
    INDEX
    Explanations

    illustrate or demonstrate examples

    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_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
     informations
    -0.94
     quels
    -0.84
     hébergement
    -0.83
     détails
    -0.82
    indications
    -0.81
    legungen
    -0.79
     profils
    -0.78
     bericht
    -0.78
     Indicators
    -0.76
    íe
    -0.76
    POSITIVE LOGITS
     illustrate
    4.88
     illustrates
    4.50
     illustrating
    4.44
     illustration
    4.22
     illustrated
    3.95
    illust
    3.67
     illustrative
    3.63
     illustrations
    3.61
     Illust
    3.56
    Illust
    3.42
    Activations Density 0.200%

    No Known Activations