Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7804
    Prev
    Next
    INDEX
    Explanations

    diffuser lens diffusion

    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
     oświet
    -0.85
    стый
    -0.69
    暗い
    -0.69
    waran
    -0.67
    Kp
    -0.65
    あえず
    -0.65
    illumin
    -0.64
    configs
    -0.64
    marginHorizontal
    -0.63
    excited
    -0.63
    POSITIVE LOGITS
     diffuser
    1.97
     diffusion
    1.65
     diff
    1.57
     lenses
    1.45
     Diffusion
    1.41
     lens
    1.41
     diffus
    1.41
    diffusion
    1.36
    Diffusion
    1.27
    Diff
    1.26
    Activations Density 0.033%

    No Known Activations