© 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. 84709
    Prev
    Next
    INDEX
    Explanations

    after time unit of

    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
     aguj
    -1.19
     cálido
    -1.16
    шению
    -1.16
    笤
    -1.07
     impresionantes
    -1.07
     embaraz
    -1.05
     acogedor
    -1.05
    ardless
    -1.04
    niß
    -1.02
    了过来
    -1.02
    POSITIVE LOGITS
     of
    6.50
    ของ
    1.82
     spent
    1.57
     של
    1.45
    of
    1.37
     on
    1.06
     Spent
    1.05
     in
    1.03
    spent
    1.02
    Spent
    1.00
    Activations Density 0.046%

    No Known Activations