© 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. 10-GEMMASCOPE-RES-131K
    7. 75534
    Prev
    Next
    INDEX
    Explanations

    assisted dying, reproduction, living, management

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

    The word "Assisted" when used as a term in medical, reproductive, or technological contexts.

    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_10/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
    籥
    -2.67
    琑
    -2.42
     we
    -2.34
     ulub
    -2.31
    
    -2.25
    孖
    -2.23
     kesin
    -2.19
    价格
    -2.16
     poussière
    -2.14
    '
    -2.13
    POSITIVE LOGITS
    媗
    3.06
    ஂ
    2.97
    that
    2.92
    This
    2.83
    殽
    2.69
    an
    2.67
    These
    2.59
    <em>
    2.55
    </h3>
    2.39
     撮っ
    2.39
    Activations Density 0.028%

    No Known Activations