© 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. 34-GEMMASCOPE-RES-131K
    7. 48282
    Prev
    Next
    INDEX
    Explanations

    dates and specific topics

    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
     pensamientos
    -1.17
     nevera
    -1.17
     tableta
    -1.17
     cafetería
    -1.15
    饜
    -1.11
     marchand
    -1.09
     luks
    -1.07
     photographe
    -1.06
     meni
    -1.05
     officier
    -1.05
    POSITIVE LOGITS
     why
    1.22
     scrutin
    0.95
    cún
    0.94
     While
    0.93
     concept
    0.91
    ţei
    0.91
     According
    0.90
     whether
    0.90
     Whether
    0.89
    我也是
    0.89
    Activations Density 0.212%

    No Known Activations