© 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. 119309
    Prev
    Next
    INDEX
    Explanations

    represented, currently, shortly, internationally

    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
     information
    -1.02
     appropriately
    -1.01
     long
    -0.98
     innumerable
    -0.93
     Because
    -0.92
     first
    -0.91
     payment
    -0.91
    --
    -0.89
     not
    -0.88
     more
    -0.88
    POSITIVE LOGITS
     vanille
    1.15
     applau
    1.09
    ッキリ
    1.08
    presumably
    1.04
     verhind
    1.02
    ixante
    1.02
     constate
    1.01
     nimmer
    1.00
     majest
    1.00
     sûre
    1.00
    Activations Density 0.040%

    No Known Activations