© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74374
    Prev
    Next
    INDEX
    Explanations

    public speaker, author, broadcaster, lecturer

    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
     they
    -1.41
    IActionResult
    -1.38
     jedną
    -1.35
     dibujado
    -1.29
     yalnızca
    -1.28
     กัน
    -1.27
     albeit
    -1.27
    ITICAL
    -1.26
    ͤ
    -1.21
     integrantes
    -1.20
    POSITIVE LOGITS
    ...-
    1.51
    ……………………
    1.41
     …)
    1.38
     wens
    1.37
     armen
    1.37
    </sup>
    1.36
     rahasia
    1.34
     on
    1.31
    ………………………………
    1.31
     aquarelle
    1.30
    Activations Density 0.055%

    No Known Activations