© 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. 130557
    Prev
    Next
    INDEX
    Explanations

    factors affecting outcomes

    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
     книге
    -1.14
     bertujuan
    -1.07
    hooter
    -1.07
     النبات
    -1.06
    paravant
    -1.05
    
    -1.05
     Tenemos
    -1.04
    鸩
    -1.02
     vecino
    -1.02
    äule
    -1.02
    POSITIVE LOGITS
     success
    1.54
     why
    1.52
     and
    1.43
     these
    1.34
     successful
    1.32
     such
    1.29
     this
    1.24
     each
    1.09
     mengapa
    1.04
     succeed
    1.02
    Activations Density 0.113%

    No Known Activations