© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93491
    Prev
    Next
    INDEX
    Explanations

    sea snail

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

    names or references containing "sea" followed by other letters, particularly in company or brand names.

    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
    そんなに
    -0.79
     soothing
    -0.78
     anges
    -0.75
     inciner
    -0.75
     zelo
    -0.75
    auf
    -0.74
     rheinland
    -0.73
     mechanized
    -0.73
     използва
    -0.73
    我会
    -0.71
    POSITIVE LOGITS
    Sea
    0.88
    nien
    0.84
     Sea
    0.81
    
    0.81
    wir
    0.75
     SCHOLAR
    0.73
    careous
    0.73
    PEI
    0.73
    ✌️
    0.71
    ню
    0.71
    Activations Density 0.025%

    No Known Activations