© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 110522
    Prev
    Next
    INDEX
    Explanations

    lush green vegetation

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of lush, green, vibrant natural environments.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    ('/');
    -0.83
     düşük
    -0.82
     солнце
    -0.79
     skvě
    -0.77
    BaseActivity
    -0.77
    IDAE
    -0.77
     Behav
    -0.76
    práv
    -0.74
     blijft
    -0.74
     солнца
    -0.74
    POSITIVE LOGITS
     lush
    3.00
     green
    2.75
     greenery
    2.58
    green
    2.30
     greener
    2.16
     vegetation
    2.13
    lush
    2.02
     verd
    1.98
    Green
    1.95
     greens
    1.84
    Activations Density 0.027%

    No Known Activations