© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40112
    Prev
    Next
    INDEX
    Explanations

    incoming calls and doors

    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
    ORG
    -1.03
     ۷
    -1.02
    虽然
    -1.02
    EACH
    -1.01
    甚至
    -0.99
    每一个
    -0.96
    ߞ
    -0.95
     حتی
    -0.92
    ilfe
    -0.92
    ียด
    -0.92
    POSITIVE LOGITS
     someone
    1.34
     two
    1.16
     incoming
    1.06
     came
    1.02
     three
    1.00
     preparing
    1.00
     organizador
    0.95
     někdo
    0.95
     somebody
    0.94
    Bö
    0.93
    Activations Density 0.009%

    No Known Activations