© 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. 107483
    Prev
    Next
    INDEX
    Explanations

    growing, developing, starting

    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
    經常
    -1.06
     verres
    -1.05
    siębior
    -0.99
    strasse
    -0.98
    🐠
    -0.97
     ._
    -0.96
    :{}
    -0.94
    !«
    -0.94
    bės
    -0.93
    ?«
    -0.93
    POSITIVE LOGITS
     there
    1.27
    Slowly
    1.20
     growth
    1.17
     support
    1.17
     younger
    1.13
     opportunities
    1.10
     talent
    1.10
    Благодаря
    1.09
     slowly
    1.09
     pockets
    1.07
    Activations Density 0.052%

    No Known Activations