© 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. 13514
    Prev
    Next
    INDEX
    Explanations

    change or update

    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
    emballage
    -1.08
     parcour
    -1.05
     inaug
    -1.01
    xFC
    -0.99
     explica
    -0.96
     intensif
    -0.96
     interro
    -0.95
    ês
    -0.94
     allé
    -0.94
     sva
    -0.92
    POSITIVE LOGITS
     including
    0.97
     cammin
    0.96
     expérimentés
    0.94
     scrivere
    0.91
     fornito
    0.90
     cambiare
    0.89
     chiedere
    0.85
     chiuso
    0.85
     zmieni
    0.84
     same
    0.84
    Activations Density 0.005%

    No Known Activations