© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 113063
    Prev
    Next
    INDEX
    Explanations

    pancreatic cancer, secretion, cysts

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

    terms related to pancreatic anatomy, conditions, and diseases.

    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
    </strong>
    -1.95
    ں
    -1.73
    躂
    -1.73
    ࿙
    -1.59
    沺
    -1.54
    的时候
    -1.53
     anderen
    -1.49
     grün
    -1.48
    leren
    -1.46
    龵
    -1.45
    POSITIVE LOGITS
    </td>
    2.20
    </h2>
    1.63
     gives
    1.63
     =
    1.58
    遐
    1.55
     decis
    1.53
     prevents
    1.52
    ");
    
    1.51
    ﺲ
    1.50
    桖
    1.50
    Activations Density 0.086%

    No Known Activations