© 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. 31520
    Prev
    Next
    INDEX
    Explanations

    mg, equiv, excess

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

    numerical values representing percentages or measurements in scientific papers.

    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
    скажите
    -0.96
    itudine
    -0.96
     бампер
    -0.88
    ahuila
    -0.85
     hundreds
    -0.84
    uleb
    -0.84
     اولیه
    -0.83
     arguments
    -0.83
    fetchall
    -0.82
    ciller
    -0.82
    POSITIVE LOGITS
    mmol
    0.98
     mmol
    0.96
    Rong
    0.91
    Teknik
    0.89
    Avocado
    0.89
    Metode
    0.88
    ведение
    0.87
    Cambio
    0.86
    équi
    0.85
    HAIR
    0.85
    Activations Density 0.004%

    No Known Activations