© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15710
    Prev
    Next
    INDEX
    Explanations

    code block closers

    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
     capturar
    -1.05
    Fitur
    -0.94
    Maar
    -0.91
    Nieuwe
    -0.91
    bahaya
    -0.90
    uniqlo
    -0.90
    yayım
    -0.90
    Kleur
    -0.90
    Artes
    -0.89
    Takk
    -0.88
    POSITIVE LOGITS
     of
    1.13
    垠
    0.88
     небольшой
    0.88
     éditions
    0.82
    จาก
    0.82
     Which
    0.82
    　
    0.80
    huizen
    0.80
    TintMode
    0.79
    转换成
    0.79
    Activations Density 0.004%

    No Known Activations