© 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. 94
    Prev
    Next
    INDEX
    Explanations

    another

    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
    因为它
    -1.16
    它
    -1.08
     ママ
    -0.98
     solcher
    -0.98
     Könige
    -0.98
     ocorrer
    -0.97
    ㌢
    -0.97
    这也
    -0.97
     takiego
    -0.96
     그것
    -0.96
    POSITIVE LOGITS
     another
    1.52
    今度は
    1.41
     again
    1.40
    こちらも
    1.39
     ebenfalls
    1.32
     more
    1.27
     ANOTHER
    1.27
     opět
    1.21
     faca
    1.16
    again
    1.11
    Activations Density 0.015%

    No Known Activations