© 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. 93437
    Prev
    Next
    INDEX
    Explanations

    numbers followed by orf

    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
     acondicionado
    -0.96
    单独
    -0.85
     لهذه
    -0.84
    かっ
    -0.84
     inglesa
    -0.84
    靦
    -0.82
    というわけで
    -0.81
    ☭
    -0.81
    当成
    -0.81
    嚇
    -0.81
    POSITIVE LOGITS
    mantel
    0.97
     '_'
    0.90
     membayar
    0.90
    გ
    0.88
    %(
    0.88
    titudine
    0.87
     _,
    0.85
    )、
    0.85
    人民
    0.84
    を読
    0.84
    Activations Density 0.002%

    No Known Activations