© 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. 48190
    Prev
    Next
    INDEX
    Explanations

    funnel, filter, feed, drain

    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_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
    Pang
    -0.71
     нрав
    -0.70
     Pang
    -0.69
     Rivière
    -0.68
    ͧ
    -0.67
     bal
    -0.66
     SOS
    -0.65
     Purge
    -0.64
    Hank
    -0.64
    働く
    -0.63
    POSITIVE LOGITS
     funnel
    5.47
     Funnel
    4.31
    fun
    2.75
    Fun
    2.38
    漏
    2.28
    FUN
    2.20
     fun
    2.20
     FUN
    2.08
     Fun
    2.06
     functor
    1.89
    Activations Density 0.041%

    No Known Activations