© 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. 27446
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    imbang
    -1.21
     transparan
    -1.09
    感じが
    -1.05
     kebersihan
    -1.04
    ～～～～
    -1.03
    定価
    -1.02
    شفى
    -1.01
    いかがでしたか
    -1.00
    〜〜
    -0.98
    Elaboración
    -0.97
    POSITIVE LOGITS
    '
    1.16
     commandés
    1.12
    ጺ
    1.08
    an
    1.02
    DA
    0.99
    也只是
    0.99
    ↵↵↵↵↵↵↵
    0.98
    "),
    0.96
    ↵↵↵↵↵
    0.96
     devenus
    0.95
    Activations Density 0.010%

    No Known Activations