© 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. 39673
    Prev
    Next
    INDEX
    Explanations

    prime minister

    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
    ...),
    -1.23
     tanken
    -1.21
     ""),
    -1.19
     şeyler
    -1.19
    =[],
    -1.16
     comité
    -1.13
     diperhatikan
    -1.12
     ceremonia
    -1.10
     rê
    -1.09
    /***
    -1.09
    POSITIVE LOGITS
    為に
    1.10
    を行い
    1.08
    也不用
    1.01
     indestru
    0.98
    に行ってきました
    0.97
     don
    0.95
    わん
    0.93
    時も
    0.93
    をしています
    0.92
    のですね
    0.92
    Activations Density 0.051%

    No Known Activations