© 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. 608
    Prev
    Next
    INDEX
    Explanations

    length scale, airfoil, radar, Page, cars, Options, printers, diode, List, Love, beam

    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
    ,
    -1.00
     Because
    -0.96
    ă
    -0.95
    !
    -0.93
     The
    -0.91
     or
    -0.90
    you
    -0.90
           
    -0.89
            
    -0.89
    '
    -0.88
    POSITIVE LOGITS
    枼
    1.13
    Ꭸ
    1.00
    actéristi
    0.98
    力は
    0.96
     această
    0.94
    なかったので
    0.94
     culoare
    0.93
    悻
    0.93
    utuhan
    0.93
     Nestlé
    0.93
    Activations Density 0.156%

    No Known Activations