© 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. 66724
    Prev
    Next
    INDEX
    Explanations

    found that

    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
     your
    -1.07
    ࿆
    -1.06
     میں
    -1.05
    gupta
    -1.05
    gesehen
    -1.02
     karena
    -1.02
    atzes
    -1.02
     Abgerufen
    -1.02
    靱
    -0.99
    靭
    -0.98
    POSITIVE LOGITS
     that
    2.47
     there
    1.27
     evidence
    1.24
     ПОД
    1.16
    THEY
    1.16
     mostaza
    1.16
    什么呢
    1.14
     față
    1.14
     campeón
    1.13
    ového
    1.08
    Activations Density 0.053%

    No Known Activations