© 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. 13793
    Prev
    Next
    INDEX
    Explanations

    resetting or updating user credentials

    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
     kaž
    -0.94
     começa
    -0.92
     here
    -0.84
    μου
    -0.84
    っており
    -0.82
     牛奶
    -0.82
     treino
    -0.81
     incele
    -0.80
    isesti
    -0.80
    žiu
    -0.80
    POSITIVE LOGITS
     new
    1.26
    重新
    1.09
     again
    1.09
     re
    1.03
    Etimo
    1.02
     ponownie
    0.99
     دوباره
    0.97
     nuovamente
    0.94
    ecé
    0.93
     recapture
    0.90
    Activations Density 0.000%

    No Known Activations