© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130152
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on organizational mission‐or‐purpose statements—phrases like “our mission/goal/focus is to…provide…” that declare what a company or group aims to do.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    to provide

    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_22/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
     for
    -1.47
     two
    -1.37
     then
    -1.35
    erschiedene
    -1.27
     several
    -1.26
     some
    -1.24
     additional
    -1.24
     separately
    -1.23
     instead
    -1.22
     without
    -1.16
    POSITIVE LOGITS
     you
    2.09
    每
    1.40
     your
    1.30
    每个
    1.27
    every
    1.20
    给你
    1.16
     igra
    1.13
    找到
    1.12
    只要
    1.11
     каждую
    1.09
    Activations Density 0.036%

    No Known Activations