© 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. 13296
    Prev
    Next
    INDEX
    Explanations

    code, citations, punctuation

    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
    pasta
    -1.10
    荜
    -1.09
    PÁG
    -1.05
     饼
    -1.03
     melalui
    -1.01
    𝛾
    -0.98
     setAddress
    -0.97
     经典
    -0.96
    worths
    -0.96
    |*
    -0.96
    POSITIVE LOGITS
    采用了
    1.19
    ,
    1.18
     lesquelles
    1.16
     ladite
    1.16
     Э
    1.08
     (
    1.04
    ложи
    1.03
     like
    1.03
    Honestly
    1.02
    𓋼
    1.00
    Activations Density 0.000%

    No Known Activations