© 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. 12920
    Prev
    Next
    INDEX
    Explanations

    `ta`, `loc`, `LIGHT`, `a`, `2`, `3`, `B`, `c`

    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
    ようです
    -1.21
    ようですが
    -1.09
    無し
    -1.07
    あっという
    -1.06
     nyaman
    -1.06
    ditionally
    -1.06
    来週
    -1.06
     alemania
    -1.03
    あぁ
    -1.03
    atiche
    -1.02
    POSITIVE LOGITS
    これ
    1.19
    參考資料
    1.16
    これは
    1.01
    Legături
    0.99
     raga
    0.99
     =
    0.98
    woners
    0.98
    Ḳ
    0.96
     culturali
    0.96
    leute
    0.95
    Activations Density 0.007%

    No Known Activations