© 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. 35450
    Prev
    Next
    INDEX
    Explanations

    hoping for, lucky if, stabilization of

    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
     Spree
    -0.89
    TypeArgs
    -0.83
    AGED
    -0.81
    索引
    -0.80
     dier
    -0.80
    STRUCTIONS
    -0.78
     bont
    -0.77
     berlin
    -0.77
    ]--;
    -0.77
    Ԁ
    -0.77
    POSITIVE LOGITS
     any
    1.22
     anything
    1.08
     merely
    1.03
     even
    1.02
    Any
    1.02
    だけでも
    1.02
     anywhere
    1.00
     immerhin
    0.98
    Anything
    0.98
    能
    0.95
    Activations Density 0.028%

    No Known Activations