© 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. 102778
    Prev
    Next
    INDEX
    Explanations

    fiscal quarters

    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
     straightforward
    -1.06
     ogrom
    -1.05
     during
    -1.03
     osoba
    -1.00
    人在
    -0.96
     nikt
    -0.93
     structures
    -0.91
     während
    -0.91
     podczas
    -0.89
     fifth
    -0.89
    POSITIVE LOGITS
     of
    1.30
     penger
    1.10
     verra
    1.09
     milliard
    1.08
     afs
    1.04
     regionale
    1.03
     tradis
    1.03
     perioden
    1.02
     spes
    1.01
     الميل
    1.01
    Activations Density 0.014%

    No Known Activations