© 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. 71712
    Prev
    Next
    INDEX
    Explanations

    home fixtures, microscopy, SEO

    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
     Perlu
    -0.93
     it
    -0.91
    علق
    -0.91
     segni
    -0.91
     conclu
    -0.89
    𝘈
    -0.89
     заключа
    -0.88
     then
    -0.88
    を行いました
    -0.86
     (_
    -0.86
    POSITIVE LOGITS
     of
    1.37
     on
    1.21
     dám
    1.05
     contenus
    1.04
     kwenye
    1.01
     Гали
    1.00
     cérami
    0.96
    źdz
    0.95
     Па
    0.93
     són
    0.91
    Activations Density 0.127%

    No Known Activations