© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 841
    Prev
    Next
    INDEX
    Explanations

    making or causing

    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
    Срок
    -1.67
     gdyby
    -1.62
    /
    -1.58
    on
    -1.56
     эту
    -1.53
    who
    -1.48
     orgánica
    -1.47
     haven
    -1.46
    that
    -1.46
     твои
    -1.39
    POSITIVE LOGITS
     a
    2.38
    gning
    1.70
     sebuah
    1.65
    lose
    1.62
     Affaires
    1.56
     pengaruh
    1.45
    zionato
    1.44
     situasi
    1.44
    lion
    1.43
    amins
    1.41
    Activations Density 0.006%

    No Known Activations