© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128447
    Prev
    Next
    INDEX
    Explanations

    The neuron detects mentions of fundraising—expressions about raising or collecting money (e.g., “raised money,” “raising funds,” “fundraising,” etc.).

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

    raising money and funds

    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
     ними
    -1.23
     sellado
    -1.20
    occasione
    -1.18
    选择
    -1.18
    CHANGE
    -1.16
    arrivo
    -1.16
    ↵
    -1.14
    Should
    -1.13
     godt
    -1.13
     primeiras
    -1.13
    POSITIVE LOGITS
     for
    2.69
     для
    1.38
     fundraising
    1.24
    مثلة
    1.23
     through
    1.20
     квітня
    1.20
     collectible
    1.13
     inför
    1.13
     during
    1.12
    สำหรับ
    1.09
    Activations Density 0.013%

    No Known Activations