© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 9779
    Prev
    Next
    INDEX
    Explanations

    chipset, display,Cars, manipulation, microprocessor

    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
     充電
    -1.02
    琉
    -1.00
     aza
    -1.00
    定食
    -1.00
    Surprisingly
    -0.95
     various
    -0.92
    予定です
    -0.92
    ἀ
    -0.92
     varied
    -0.91
    typeName
    -0.91
    POSITIVE LOGITS
     outskirts
    1.12
     оконча
    1.08
     queste
    1.07
     yağı
    1.06
     entsprechen
    1.05
     erbjud
    1.05
     gewährle
    1.04
    はこの
    1.02
     "`
    1.01
    璟
    0.98
    Activations Density 0.048%

    No Known Activations