© 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. 10-GEMMASCOPE-RES-131K
    7. 59372
    Prev
    Next
    INDEX
    Explanations

    Mendel, Mendocino, Mendoza

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

    words containing or related to "Mend" like "Mendoza," "Mendelsonian," and "mending."

    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
    }
    -3.36
    閬
    -2.64
    liği
    -2.56
    eterminate
    -2.47
    ',
    -2.41
    ğın
    -2.41
    geblich
    -2.31
     です
    -2.28
    ');
    -2.28
    vantaged
    -2.25
    POSITIVE LOGITS
    ),
    3.16
    ↵
    2.91
    頫
    2.84
    ER
    2.55
    S
    2.48
    h
    2.47
    他们在
    2.44
    ’
    2.42
    不论
    2.34
    with
    2.30
    Activations Density 0.002%

    No Known Activations