© 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. 34-GEMMASCOPE-RES-131K
    7. 83748
    Prev
    Next
    INDEX
    Explanations

    software licenses and terms

    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_34/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
    無し
    -1.07
     like
    -1.02
    にします
    -0.98
     aveo
    -0.94
    んですか
    -0.93
    之地
    -0.93
    んでしょう
    -0.91
     italia
    -0.91
    madre
    -0.90
    様な
    -0.88
    POSITIVE LOGITS
    Lá
    1.11
     yapan
    1.10
    thoven
    1.08
     yapmak
    1.07
    IENTS
    1.04
     mums
    1.03
     pengobatan
    1.02
    噢
    1.02
    ophore
    1.02
     kdy
    1.01
    Activations Density 0.122%

    No Known Activations