© 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. 34-GEMMASCOPE-RES-131K
    7. 57663
    Prev
    Next
    INDEX
    Explanations

    innovative improvements and new technologies

    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
    нера
    -1.16
    實
    -1.03
    mechanism
    -1.03
     Ucraina
    -1.02
    isling
    -1.02
    谄
    -1.00
     aproveitar
    -1.00
    ãy
    -1.00
     extranjeros
    -0.99
     apparti
    -0.98
    POSITIVE LOGITS
     demonstrators
    1.58
     pretended
    1.20
     innovative
    1.16
     foreseen
    1.14
    XXL
    1.09
     novel
    1.07
     KPIs
    1.07
    Nowadays
    1.06
     new
    1.02
     evermore
    1.02
    Activations Density 0.144%

    No Known Activations