© 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. 10-GEMMASCOPE-RES-131K
    7. 90825
    Prev
    Next
    INDEX
    Explanations

    ask to look or comment

    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_10/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
     you
    -1.60
     but
    -1.38
     to
    -1.16
     ekolog
    -1.09
    が欲しい
    -1.06
    ）　
    -1.03
    polski
    -1.03
    ibat
    -1.02
     wszystkie
    -1.02
    %;
    -1.01
    POSITIVE LOGITS
    źnie
    1.23
    ❖
    1.16
    ográfica
    1.13
    доба
    1.13
    ètres
    1.13
     résultat
    1.10
     kembali
    1.08
     has
    1.08
    mappedBy
    1.05
    fucking
    1.05
    Activations Density 0.059%

    No Known Activations