© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37730
    Prev
    Next
    INDEX
    Explanations

    All Rights Reserved

    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_34/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
    枳
    -0.88
    🥑
    -0.82
     उसने
    -0.82
     różnych
    -0.80
     distintos
    -0.80
     crea
    -0.79
     zuerst
    -0.79
    플
    -0.79
     lux
    -0.78
     indepen
    -0.78
    POSITIVE LOGITS
     Just
    1.07
    スペック
    0.86
     but
    0.85
    連載
    0.85
     JUST
    0.82
    [][]
    0.82
     Always
    0.82
     sekaligus
    0.81
     Basically
    0.80
     pekerjaan
    0.80
    Activations Density 0.001%

    No Known Activations