© 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. 57930
    Prev
    Next
    INDEX
    Explanations

    sequence of actions or states

    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
     évek
    -1.19
     niitä
    -1.03
     campagnes
    -1.02
    weekly
    -1.00
    bestand
    -0.98
    欤
    -0.96
    Weekly
    -0.96
     nagyobb
    -0.96
    Later
    -0.95
    among
    -0.95
    POSITIVE LOGITS
     almost
    1.32
     before
    1.29
     continue
    1.23
     continuing
    1.23
     past
    1.21
     still
    1.19
     while
    1.18
     completing
    1.18
     initiating
    1.11
     momentum
    1.09
    Activations Density 0.038%

    No Known Activations