© 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. 34-GEMMASCOPE-RES-131K
    7. 54209
    Prev
    Next
    INDEX
    Explanations

    UI transitions and animations

    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_34/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
     enzy
    -0.84
     secretion
    -0.80
    bridi
    -0.78
     sınıf
    -0.75
     hydrolysis
    -0.74
    Respondents
    -0.71
    얗
    -0.71
     Weights
    -0.70
     dissection
    -0.70
     USB
    -0.69
    POSITIVE LOGITS
     transition
    1.39
     Transition
    1.19
    transition
    1.18
    Transition
    1.18
     transitions
    1.16
     shared
    1.11
     transitional
    1.10
     exit
    1.07
     transitioning
    1.06
    共享
    1.05
    Activations Density 0.016%

    No Known Activations