© 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. 37978
    Prev
    Next
    INDEX
    Explanations

    life and time units

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

    words related to "life" or abstract concepts like "job", "point", "price" and "lesson".

    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
    capable
    -0.91
    wrote
    -0.89
    amazing
    -0.81
    יקר
    -0.81
    Produced
    -0.81
    女孩
    -0.79
    manufactured
    -0.78
    eniem
    -0.78
    zur
    -0.78
    кре
    -0.77
    POSITIVE LOGITS
     well
    4.06
    Well
    2.64
     dobrze
    2.39
     Well
    2.36
    well
    2.33
     jól
    2.30
     хорошо
    2.25
     WELL
    2.16
     dobře
    2.08
     hyvin
    2.06
    Activations Density 0.020%

    No Known Activations