© 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. 95403
    Prev
    Next
    INDEX
    Explanations

    political representatives

    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
     surging
    -1.32
    不论
    -1.26
    ']
    -1.20
     Einzelnen
    -1.20
     -
    -1.20
     nehmen
    -1.19
    Z
    -1.19
     ….
    -1.16
     они
    -1.16
    ")
    -1.16
    POSITIVE LOGITS
     pertenec
    1.51
    habited
    1.45
    ܖ
    1.40
     yến
    1.40
    angering
    1.40
    habitants
    1.40
    whelmed
    1.39
     who
    1.38
    깽
    1.38
    
    1.37
    Activations Density 0.036%

    No Known Activations