© 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. 93438
    Prev
    Next
    INDEX
    Explanations

    oral dose, daily, tier of

    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
     manguera
    -1.09
    他就
    -1.09
     cómoda
    -1.05
     moverse
    -1.00
     Widers
    -0.99
    Numerous
    -0.98
     Vorg
    -0.97
     приводит
    -0.97
     MANY
    -0.96
    に行って
    -0.96
    POSITIVE LOGITS
     again
    1.30
    Ḫ
    1.27
    -.-
    1.27
    eryn
    1.23
    rrrrrrrr
    1.16
     azule
    1.10
    闪过
    1.09
     likewise
    1.09
    mmmmmm
    1.07
     palme
    1.06
    Activations Density 0.006%

    No Known Activations