© 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. 34-GEMMASCOPE-RES-131K
    7. 116937
    Prev
    Next
    INDEX
    Explanations

    display:none

    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_34/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
    wwe
    -0.84
     hamilton
    -0.81
     angen
    -0.75
     licht
    -0.75
    czyki
    -0.75
     lying
    -0.74
     unprotected
    -0.73
     Kaspersky
    -0.73
    eek
    -0.72
     emailAlready
    -0.71
    POSITIVE LOGITS
     hidden
    2.17
    hidden
    2.06
    isHidden
    1.89
    Hidden
    1.80
     hide
    1.76
     Hidden
    1.75
     concealed
    1.64
    hide
    1.61
    Hide
    1.48
     Hide
    1.48
    Activations Density 0.021%

    No Known Activations