© 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. 22-GEMMASCOPE-RES-131K
    7. 73300
    Prev
    Next
    INDEX
    Explanations

    styles and taste

    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
     bawat
    -1.24
     Each
    -1.05
    ziesz
    -1.03
     toul
    -1.01
     саны
    -1.00
     iniqu
    -0.98
     प्रत्येक
    -0.96
     séances
    -0.96
     syndical
    -0.94
     munici
    -0.94
    POSITIVE LOGITS
     style
    1.26
     stylu
    1.15
     estilo
    1.14
    ﻻ
    1.07
     Kontakte
    1.05
     but
    1.05
    ềm
    1.05
     pogod
    1.03
     opposite
    1.02
     phù
    1.02
    Activations Density 0.069%

    No Known Activations