© 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. 10-GEMMASCOPE-RES-131K
    7. 20431
    Prev
    Next
    INDEX
    Explanations

    Change.org petitions

    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_10/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
    urtstag
    -1.37
    gigabyte
    -1.34
     \&
    -1.34
    The
    -1.32
    ֽ
    -1.23
    確かに
    -1.21
    In
    -1.20
    </i>
    -1.20
     utter
    -1.20
    чем
    -1.18
    POSITIVE LOGITS
     GoFundMe
    1.70
     “
    1.36
    幛
    1.33
     to
    1.22
    }=
    1.21
     映画
    1.13
     crowdfunding
    1.09
    trooper
    1.08
     Abends
    1.05
    ずに
    1.03
    Activations Density 0.024%

    No Known Activations