© 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. 22-GEMMASCOPE-RES-131K
    4. 66313
    Prev
    Next
    INDEX
    Explanations

    dimensions and measurements

    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
     all
    -1.28
     particularly
    -1.23
    
    -1.14
     Warenkorb
    -1.12
     ある
    -1.09
     など
    -1.08
    或
    -1.06
     system
    -1.06
     many
    -1.05
     helps
    -1.03
    POSITIVE LOGITS
     size
    1.36
     diameter
    1.15
     width
    1.15
    此时的
    1.01
     suministro
    1.00
    接下来的
    0.98
    まれた
    0.97
    嗫
    0.97
    size
    0.97
    ミネ
    0.95
    Activations Density 0.046%

    No Known Activations