© 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. 10-GEMMASCOPE-RES-131K
    7. 7320
    Prev
    Next
    INDEX
    Explanations

    fifth circuit clerk

    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
     incluso
    -1.48
     função
    -1.42
     what
    -1.42
     ἐκ
    -1.41
     even
    -1.38
     αὐτ
    -1.38
     chré
    -1.35
     witty
    -1.30
     Música
    -1.28
     mesmo
    -1.23
    POSITIVE LOGITS
    ❗️
    1.51
     militä
    1.49
    ⭐️
    1.49
    Procedimento
    1.49
    ִּ
    1.38
     Daar
    1.38
     ','
    1.35
    ⁉
    1.33
    If
    1.31
    &
    1.31
    Activations Density 0.111%

    No Known Activations