© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109617
    Prev
    Next
    INDEX
    Explanations

    refining and perfecting

    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_34/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
    ),),
    -0.96
     немає
    -0.95
    ]--;
    -0.95
     profundas
    -0.91
    好像是
    -0.89
    並不是
    -0.88
    ஂ
    -0.86
     který
    -0.85
    ISBN
    -0.85
    全部
    -0.84
    POSITIVE LOGITS
     refine
    1.27
    refine
    1.18
     perfecting
    1.14
     finer
    1.12
     Refining
    1.11
    Refinement
    1.07
     FINE
    1.06
     👌
    1.05
     refining
    1.03
     polishing
    1.00
    Activations Density 0.023%

    No Known Activations