© 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. 40106
    Prev
    Next
    INDEX
    Explanations

    website declarations and licenses

    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
    -1.02
    Ｓ
    -0.86
    chè
    -0.85
    ','',
    -0.84
    ATURES
    -0.84
    Ｆ
    -0.83
    ...

    -0.82
    ">

    -0.82
    !="")
    -0.81
    '])){

    -0.81
    POSITIVE LOGITS
     également
    1.05
    办公
    0.96
    writerow
    0.92
     maravillas
    0.91
     búsquedas
    0.91
    icata
    0.89
    どうしよう
    0.88
    onora
    0.88
    ticons
    0.88
    GroupLayout
    0.87
    Activations Density 0.166%
    No Known Activations