© 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. 39975
    Prev
    Next
    INDEX
    Explanations

    addresses and zip codes

    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
     you
    -1.78
     äusser
    -1.52
     that
    -1.50
     ehemalige
    -1.48
     tiefen
    -1.43
     Abstand
    -1.41
     today
    -1.39
     Ausblick
    -1.38
     their
    -1.38
     Absicht
    -1.37
    POSITIVE LOGITS
    erráneo
    1.59
    😰
    1.41
    ']),
    1.41
    ——–
    1.38
    ”،
    1.38
    ]),
    1.38
     conster
    1.38
     pelu
    1.36
    ✂
    1.35
     palme
    1.34
    Activations Density 0.008%

    No Known Activations