© 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. 21241
    Prev
    Next
    INDEX
    Explanations

    acronyms like FRS, AP, AGP

    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_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
    ).
    -2.50
    栳
    -1.98
    でしたが
    -1.85
    睨
    -1.73
     município
    -1.58
    ’.
    -1.55
    ellidos
    -1.55
    
    -1.55
    ministrazione
    -1.55
    ný
    -1.55
    POSITIVE LOGITS
     throng
    1.98
     laborious
    1.92
     entwick
    1.84
    чом
    1.76
    apprendre
    1.76
     dogged
    1.75
    These
    1.75
    indépendance
    1.74
    setzen
    1.73
    s
    1.70
    Activations Density 0.004%

    No Known Activations