© 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. 22-GEMMASCOPE-RES-131K
    7. 12517
    Prev
    Next
    INDEX
    Explanations

    political parties and politicians

    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_22/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
     eventuell
    -1.24
     agak
    -1.20
     män
    -1.17
     parfois
    -1.16
     nieco
    -1.14
     relativement
    -1.10
     länder
    -1.10
     geniales
    -1.09
    Sometimes
    -1.08
    Possibly
    -1.08
    POSITIVE LOGITS
     you
    1.30
    ówn
    1.18
     tonight
    1.15
     ask
    1.13
     deliver
    1.11
    -|
    1.11
    べて
    1.10
     want
    1.09
     doesn
    1.09
    :"-"`
    1.06
    Activations Density 0.041%

    No Known Activations