© 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. 75325
    Prev
    Next
    INDEX
    Explanations

    code structure and english words

    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
     similarly
    -1.30
     plaît
    -1.21
     other
    -1.19
     this
    -1.12
     when
    -1.08
     hypertension
    -1.06
     embarazada
    -1.04
     saurait
    -1.00
     Java
    -0.97
     bulan
    -0.96
    POSITIVE LOGITS
    휩
    1.17
    Aire
    1.11
     Nelle
    1.09
    Etimología
    1.08
    بسم
    1.08
    Arbe
    1.07
     voies
    1.05
    棡
    1.04
     сказать
    1.04
    importation
    1.02
    Activations Density 0.000%

    No Known Activations