© 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. 34-GEMMASCOPE-RES-131K
    7. 83795
    Prev
    Next
    INDEX
    Explanations

    communication platforms and forums

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

    The neuron activates on phrases that describe something being offered or provided—e.g. “provides a platform,” “is an internal forum,” “offered students a rare opportunity,” etc.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     ras
    -0.80
    cluster
    -0.75
     Số
    -0.74
     tampa
    -0.72
    Boot
    -0.71
     barat
    -0.70
     segnale
    -0.69
     kue
    -0.68
    かれる
    -0.66
    солю
    -0.65
    POSITIVE LOGITS
     forum
    4.78
     forums
    4.13
    forum
    3.36
     Forum
    3.03
    Forum
    2.84
     platform
    2.83
     venue
    2.75
     Forums
    2.66
     platforms
    2.61
    forums
    2.61
    Activations Density 0.067%

    No Known Activations