© 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. 35551
    Prev
    Next
    INDEX
    Explanations

    calls for requests

    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
    その
    -1.19
    人には
    -1.15
     humili
    -1.08
     детских
    -1.05
    阉
    -1.04
    (
    -1.02
     ignore
    -1.02
     知道
    -1.00
    崭
    -0.98
    敷地
    -0.98
    POSITIVE LOGITS
     called
    1.41
    Called
    1.20
     ję
    1.19
     chiama
    1.18
     CALLED
    1.14
     vandaag
    1.14
     quits
    1.13
     raccont
    1.13
     esperti
    1.13
     アクセサリー
    1.12
    Activations Density 0.024%

    No Known Activations