© 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. 71830
    Prev
    Next
    INDEX
    Explanations

    often modify adjectives or participles

    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
     this
    -1.44
     noe
    -1.28
    ći
    -1.22
     now
    -1.18
     Nous
    -1.16
    ⌉
    -1.14
     Temos
    -1.10
    )))))
    -1.09
    ‵
    -1.09
     Rés
    -1.06
    POSITIVE LOGITS
     nawet
    1.48
     razões
    1.38
     endgül
    1.35
     offiziellen
    1.24
     problemów
    1.23
    2
    1.23
    however
    1.21
    何が
    1.21
     jedes
    1.19
     даже
    1.18
    Activations Density 0.118%

    No Known Activations