© 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. 12521
    Prev
    Next
    INDEX
    Explanations

    names followed by said

    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
    thasone
    -0.94
     seleccionamos
    -0.90
     Parece
    -0.89
     Obtén
    -0.88
     esetén
    -0.86
     siitä
    -0.84
     grasses
    -0.84
     jotka
    -0.84
     Hemos
    -0.83
     postIndex
    -0.83
    POSITIVE LOGITS
     ferie
    0.98
     misto
    0.92
     salg
    0.86
     sosis
    0.86
     lata
    0.86
    期刊论文
    0.85
     تصریح
    0.85
    mäs
    0.84
    𝑊
    0.84
    Diámetro
    0.83
    Activations Density 0.004%

    No Known Activations