© 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. 22-GEMMASCOPE-RES-131K
    4. 33877
    Prev
    Next
    INDEX
    Explanations

    phone numbers and postal 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_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
     venez
    -1.43
     }^{
    -1.43
     QtWidgets
    -1.36
    mathrm
    -1.35
     :
    -1.33
    が起こ
    -1.32
     }^{\
    -1.30
    Mm
    -1.30
    АР
    -1.30
    ♮
    -1.27
    POSITIVE LOGITS
    最も
    1.39
    8
    1.30
    かせて
    1.25
    で一番
    1.20
    に行って
    1.16
     establecidos
    1.16
     proberen
    1.15
     gemeinsamen
    1.15
    んでしょう
    1.13
     or
    1.13
    Activations Density 0.017%

    No Known Activations