© 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. 22-GEMMASCOPE-RES-131K
    7. 68983
    Prev
    Next
    INDEX
    Explanations

    pharmacokinetics

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

    years written in numeric format, particularly in the format "19XX" or "20XX".

    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
     who
    -1.63
     recientes
    -1.09
     already
    -1.09
     yesterday
    -1.07
     today
    -1.06
    已经
    -1.02
     miércoles
    -0.99
     desapar
    -0.99
     zeitung
    -0.98
     reciente
    -0.95
    POSITIVE LOGITS
     赤ちゃん
    1.23
    donde
    1.10
    JHEP
    1.06
    гол
    1.05
    isLoaded
    1.02
     Şi
    1.02
    divarius
    1.01
     presto
    0.98
     行っ
    0.97
    toft
    0.97
    Activations Density 0.007%

    No Known Activations