© 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. 34-GEMMASCOPE-RES-131K
    7. 48558
    Prev
    Next
    INDEX
    Explanations

    students of and from

    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
    遢
    -1.16
     pensare
    -1.09
     comunicare
    -1.04
     preved
    -1.02
    人的
    -1.02
    ↵
    -1.02
    趿
    -1.02
     Adult
    -1.00
    子的
    -0.99
    呖
    -0.99
    POSITIVE LOGITS
     who
    2.27
     enrolled
    1.52
    athletes
    1.46
     from
    1.40
     studying
    1.39
    
    1.37
    刧
    1.25
    MAXN
    1.23
     whose
    1.22
    czę
    1.21
    Activations Density 0.028%

    No Known Activations