© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9406
    Prev
    Next
    INDEX
    Explanations

    processes and stages of development

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

    words related to biological processes and developmental programs in cellular biology.

    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_10/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
     !!!!!
    -1.92
     !!!!
    -1.81
     .......
    -1.72
    阏
    -1.70
     zurückge
    -1.70
    -\\
    -1.69
    簠
    -1.68
     merkwür
    -1.63
     ........
    -1.59
     ï
    -1.59
    POSITIVE LOGITS
    There
    2.09
    Since
    1.93
    After
    1.75
    Shortly
    1.72
    Although
    1.71
    Before
    1.68
     not
    1.66
    Some
    1.65
    According
    1.65
    Many
    1.63
    Activations Density 0.592%

    No Known Activations