© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36490
    Prev
    Next
    INDEX
    Explanations

    shopping at, opportunity to, combined testing

    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
     солнца
    -1.20
     Accesat
    -1.13
    必
    -1.11
     laughed
    -1.09
     خطر
    -1.07
    Ergebnisse
    -1.04
    这些
    -1.03
    etat
    -1.02
    必要
    -1.01
     científico
    -1.00
    POSITIVE LOGITS
     our
    2.38
     your
    2.14
     we
    1.80
     you
    1.58
    our
    1.23
     Our
    1.20
     mūsų
    1.13
     vogliamo
    1.13
    your
    1.13
    ünk
    1.12
    Activations Density 0.003%

    No Known Activations