© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38804
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and code snippets

    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
    などの
    -1.09
    などが
    -1.07
     to
    -1.01
    などを
    -0.97
    なども
    -0.97
     JScrollPane
    -0.96
     mentioned
    -0.95
     AspNetCore
    -0.92
    ariConfig
    -0.91
    걍
    -0.91
    POSITIVE LOGITS
    ようです
    1.17
    場所で
    1.13
    場所に
    1.05
    ACEAE
    1.02
    ektiv
    0.99
    cocho
    0.97
    Spéc
    0.96
     we
    0.95
    得分
    0.94
    </i>
    0.94
    Activations Density 0.008%

    No Known Activations