© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12032
    Prev
    Next
    INDEX
    Explanations

    value, cherish, treasured

    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_10/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
     Almost
    -1.71
     with
    -1.69
    
    -1.53
    🅣
    -1.52
    imetsu
    -1.51
     soát
    -1.47
     Some
    -1.46
     Hundreds
    -1.43
    josé
    -1.43
    体は
    -1.41
    POSITIVE LOGITS
    鸲
    1.72
    who
    1.59
    卝
    1.52
    particularly
    1.48
    want
    1.48
    renowned
    1.47
     takie
    1.46
     estabilidad
    1.45
     recuperação
    1.44
     taką
    1.43
    Activations Density 0.028%

    No Known Activations