© 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. 70315
    Prev
    Next
    INDEX
    Explanations

    FB abbreviation

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

    The neuron is strongly triggered by occurrences of the token “FB.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     –
    -2.92
    </h2>
    -2.78
    </sup>
    -2.59
    ).
    -2.50
    什么的
    -2.38
    をチェック
    -2.34
     −
    -2.23
    </td>
    -2.20
     欣赏
    -2.19
    芣
    -2.19
    POSITIVE LOGITS
    櫺
    2.70
    síða
    2.52
    💧
    2.47
    廰
    2.47
    廨
    2.44
    ('');
    2.30
     間取り
    2.28
    💓
    2.27
    😰
    2.27
     Signalez
    2.25
    Activations Density 0.004%

    No Known Activations