© 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. 79665
    Prev
    Next
    INDEX
    Explanations

    I verb

    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
    が
    -1.76
     ندارد
    -1.54
    ÁR
    -1.48
    さすがに
    -1.45
     one
    -1.45
    などを
    -1.45
     ↓,
    -1.44
    瑧
    -1.44
     that
    -1.44
     排骨
    -1.41
    POSITIVE LOGITS
     It
    2.05
    為に
    1.92
     You
    1.75
    事が
    1.59
    場所に
    1.55
    }
    1.55
    を選択
    1.52
    还得
    1.51
    場所で
    1.51
     incluido
    1.44
    Activations Density 0.089%

    No Known Activations