© 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. 44303
    Prev
    Next
    INDEX
    Explanations

    phone numbers

    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
     onderdeel
    -1.63
     Nieuws
    -1.52
    ríamos
    -1.52
    iembre
    -1.49
     forbin
    -1.48
    ordnet
    -1.46
     Paweł
    -1.46
    usually
    -1.41
     distinto
    -1.39
     detaljer
    -1.39
    POSITIVE LOGITS
     creating
    1.78
     their
    1.65
     making
    1.52
     placing
    1.49
     doing
    1.49
     putting
    1.49
     some
    1.48
     establishing
    1.44
     what
    1.44
     by
    1.43
    Activations Density 0.018%

    No Known Activations