© 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. 10-GEMMASCOPE-RES-131K
    7. 1238
    Prev
    Next
    INDEX
    Explanations

    cell or cellular structure

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

    references to cells in biological, technological, or computational contexts.

    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
    ㍉
    -2.19
    腘
    -2.17
    んですが
    -2.17
     champignons
    -2.13
     hunne
    -2.08
    ？！”
    -2.05
     Valuable
    -2.02
    餮
    -2.02
     gekle
    -1.99
     哪些
    -1.97
    POSITIVE LOGITS
    )
    3.22
    h
    2.30
     our
    2.27
    л
    2.25
     other
    2.23
    其他
    2.16
     '
    2.13
    m
    2.11
    c
    2.08
    with
    2.06
    Activations Density 0.052%

    No Known Activations