© 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. 75370
    Prev
    Next
    INDEX
    Explanations

    Q: followed by questions

    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
    beten
    -1.17
     república
    -1.07
     hierv
    -1.05
     mengam
    -1.04
    новые
    -1.04
    parken
    -1.02
     adulto
    -1.00
     сада
    -0.99
     pandas
    -0.98
     kreis
    -0.98
    POSITIVE LOGITS
     BOTH
    1.26
    队员
    1.16
    both
    1.12
     lleno
    1.05
     both
    1.05
     disciplines
    1.02
    طقة
    1.01
    钣
    0.99
     ジャ
    0.98
     matka
    0.95
    Activations Density 0.001%

    No Known Activations