© 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. 15388
    Prev
    Next
    INDEX
    Explanations

    names and words introducing specific entities

    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
     of
    -1.08
     overall
    -1.05
     relevant
    -1.01
     okno
    -0.96
     corredores
    -0.91
    kuat
    -0.89
    siye
    -0.87
    べし
    -0.86
    شفى
    -0.86
     آیفون
    -0.85
    POSITIVE LOGITS
     duod
    1.17
     ciphertext
    1.05
     microcontroller
    1.04
    anyahu
    1.03
    otechnology
    0.97
    Подробнее
    0.96
     よう
    0.96
     destroyers
    0.95
     sider
    0.95
    使いやすい
    0.94
    Activations Density 0.003%

    No Known Activations