© 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. 13482
    Prev
    Next
    INDEX
    Explanations

    lifecycle methods

    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
    馓
    -1.47
     bunda
    -1.39
     sapatos
    -1.38
    糁
    -1.38
    
    -1.36
     célè
    -1.35
     faciliter
    -1.33
     عناصر
    -1.33
     rembourse
    -1.31
     délicieux
    -1.31
    POSITIVE LOGITS
     Before
    1.81
     not
    1.74
     after
    1.67
     Every
    1.59
     before
    1.58
     After
    1.55
    After
    1.48
     When
    1.47
     or
    1.43
     h
    1.40
    Activations Density 0.011%

    No Known Activations