© 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. 22-GEMMASCOPE-RES-131K
    7. 15620
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    corrhi
    -1.80
     וכן
    -1.80
    PENDAHULUAN
    -1.63
     nena
    -1.59
    ことなく
    -1.58
     mikina
    -1.58
    읖
    -1.52
    Жизнь
    -1.52
    ៖
    -1.49
    معلومات
    -1.48
    POSITIVE LOGITS
    ↵↵
    1.94
    $
    1.83
    <>
    1.75
    >
    1.70
    *
    1.66
    ↵↵↵
    1.66
    ]
    1.59
    ”
    1.53
    </u>
    1.51
     
    1.51
    Activations Density 0.003%

    No Known Activations