© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 39631
    Prev
    Next
    INDEX
    Explanations

    removal, discharge, dissipation, detoxification

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

    concepts related to removal, release, or expulsion of substances from a system or body.

    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_22/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
     impenetrable
    -0.88
    amship
    -0.87
    meier
    -0.85
    取締役
    -0.85
    racion
    -0.84
    理由は
    -0.80
    setDisabled
    -0.80
    minos
    -0.80
    置いて
    -0.80
    わかります
    -0.80
    POSITIVE LOGITS
    处理
    1.25
     excess
    1.20
     Excess
    0.98
    処理
    0.97
    excess
    0.96
     öt
    0.95
     처리
    0.95
    通过
    0.95
     manej
    0.94
    Dealing
    0.93
    Activations Density 0.102%

    No Known Activations