© 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. 92886
    Prev
    Next
    INDEX
    Explanations

    item, growth, soluble, efficient, characterization

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

    numbers in various contexts, including dates, numerical values, and identifiers.

    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
    ibili
    -0.90
    JOE
    -0.81
    есть
    -0.81
     handlebar
    -0.81
    alore
    -0.81
    髂
    -0.80
    lets
    -0.79
     باید
    -0.79
     اگر
    -0.77
    fide
    -0.77
    POSITIVE LOGITS
     soak
    0.96
     trading
    0.89
     soaked
    0.89
     trade
    0.84
     sold
    0.84
     also
    0.82
     sell
    0.82
     drop
    0.75
     dropping
    0.75
     weight
    0.74
    Activations Density 0.002%

    No Known Activations