© 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. 12268
    Prev
    Next
    INDEX
    Explanations

    gas mixtures

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

    technical and industrial terms in product specifications and patents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     for
    -1.13
     now
    -0.90
     as
    -0.84
    燭
    -0.84
     stellar
    -0.81
     battling
    -0.81
     often
    -0.77
     proactive
    -0.77
     at
    -0.76
     with
    -0.76
    POSITIVE LOGITS
     maniere
    1.10
     artig
    1.07
     multicolore
    1.04
    WAII
    0.94
    structed
    0.91
     bombe
    0.91
    various
    0.91
     
    0.90
     neuve
    0.90
    𓁹
    0.90
    Activations Density 0.004%

    No Known Activations