© 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. 12202
    Prev
    Next
    INDEX
    Explanations

    reproductive recruitment individuals

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

    scientific content about plant and tree species and their growth patterns.

    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
     postępo
    -0.78
     biome
    -0.75
     forests
    -0.74
    forests
    -0.73
    pawn
    -0.73
     spruce
    -0.72
    川崎
    -0.72
    榊
    -0.71
    correlation
    -0.71
     teda
    -0.71
    POSITIVE LOGITS
     db
    1.05
     DB
    1.05
     individuals
    0.94
     recruit
    0.89
     recording
    0.87
    個人
    0.84
     recruitment
    0.82
    individuals
    0.81
     reproductive
    0.80
     cover
    0.79
    Activations Density 0.019%

    No Known Activations