© 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. 23626
    Prev
    Next
    INDEX
    Explanations

    questions after lists

    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
    matical
    -1.13
     kré
    -1.12
     anla
    -1.03
    黑的
    -1.03
    mainen
    -1.02
    ?=
    -1.02
    periode
    -1.02
     storie
    -0.99
     publik
    -0.97
    uuuu
    -0.97
    POSITIVE LOGITS
     what
    3.06
     how
    2.77
     describe
    2.59
     why
    2.58
     explain
    2.36
     which
    2.25
     What
    2.25
     discuss
    1.99
     Describe
    1.98
     Why
    1.91
    Activations Density 0.204%

    No Known Activations