© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11484
    Prev
    Next
    INDEX
    Explanations

    rounding to nearest powers of ten

    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
     ícone
    -1.20
    鱘
    -1.13
    Actually
    -1.09
    meine
    -1.08
     väldigt
    -1.07
     มัน
    -1.05
     banheiro
    -1.05
     tény
    -1.04
    Елена
    -1.02
    спасибо
    -1.02
    POSITIVE LOGITS
    0
    1.35
     H
    0.97
     J
    0.95
     
    0.94
     biet
    0.94
     (
    0.90
    s
    0.89
     Zur
    0.89
     new
    0.88
    子の
    0.87
    Activations Density 0.028%

    No Known Activations