© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 38829
    Prev
    Next
    INDEX
    Explanations

    все работающие файлы и данные

    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
    臜
    -2.86
    敺
    -2.64
    踯
    -2.55
            
    -2.53
    coloriage
    -2.50
     سایر
    -2.50
    喈
    -2.50
    ’
    -2.47
     ſta
    -2.41
    歘
    -2.38
    POSITIVE LOGITS
    there
    2.95
    as
    2.61
    )
    2.55
    Semua
    2.53
    Mereka
    2.53
    𖧵
    2.50
    𖣘
    2.47
    after
    2.38
     With
    2.33
     There
    2.25
    Activations Density 0.001%

    No Known Activations