© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 127830
    Prev
    Next
    INDEX
    Explanations

    brewing, expecting, starting

    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
     chré
    -2.53
    ﻷ
    -2.48
    ﷲ
    -2.31
    ﻹ
    -2.20
    öra
    -2.20
    ﻻ
    -2.17
     anúncios
    -2.13
    ﺀ
    -2.09
    ׇ
    -2.08
    ίων
    -2.02
    POSITIVE LOGITS
     médec
    2.34
     оружи
    2.14
    ִּ
    1.98
     team
    1.97
    ּוֹ
    1.92
     Кубка
    1.84
     last
    1.84
     possible
    1.83
    шных
    1.80
    комплект
    1.79
    Activations Density 4.266%

    No Known Activations