© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 38831
    Prev
    Next
    INDEX
    Explanations

    interior design and decor

    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_22/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
     саны
    -1.48
     or
    -1.41
    ଵ
    -1.36
     pueden
    -1.27
    ("")){
    -1.27
     môžu
    -1.24
     narzęd
    -1.24
     erfolgreiche
    -1.23
     jedną
    -1.23
    สามารถ
    -1.20
    POSITIVE LOGITS
     modern
    1.38
     النبات
    1.27
    ﻻ
    1.20
     bouteille
    1.20
     pfalz
    1.16
     sentiers
    1.15
     MwSt
    1.14
     XVIII
    1.13
    ?!”
    1.09
     tamu
    1.09
    Activations Density 0.026%

    No Known Activations