© 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. 128824
    Prev
    Next
    INDEX
    Explanations

    famous internationally

    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
     schlechter
    -1.40
     скриншот
    -1.23
    获取
    -1.19
     you
    -1.18
    だけど
    -1.16
     working
    -1.15
    และ
    -1.13
     отель
    -1.12
     kwenye
    -1.12
     diferentes
    -1.12
    POSITIVE LOGITS
     isInitialized
    1.33
     certamen
    1.20
     hitherto
    1.20
    饷
    1.13
    Ǵ
    1.12
     valg
    1.12
    幹線
    1.11
    ⾦
    1.11
     साधारण
    1.10
    implicitly
    1.10
    Activations Density 0.040%

    No Known Activations