© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99715
    Prev
    Next
    INDEX
    Explanations

    prior to

    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
     banane
    -1.38
     basically
    -1.32
     tica
    -1.31
     disiplin
    -1.25
     tadi
    -1.20
    Basically
    -1.16
     provoque
    -1.15
     régime
    -1.13
    atious
    -1.13
    basically
    -1.13
    POSITIVE LOGITS
     Krieges
    1.38
    Exam
    1.20
    etine
    1.16
     gitara
    1.13
    คือ
    1.12
    ּוֹ
    1.09
    祖
    1.09
     harms
    1.07
     rapidamente
    1.05
    zorg
    1.05
    Activations Density 0.654%

    No Known Activations