© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98919
    Prev
    Next
    INDEX
    Explanations

    of the following

    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
     several
    -1.16
     such
    -1.03
    Several
    -1.02
     кілька
    -0.90
     Several
    -0.90
     many
    -0.90
     Weltkrieg
    -0.86
     Nachbarn
    -0.84
     highest
    -0.84
     certain
    -0.80
    POSITIVE LOGITS
     the
    2.00
     celor
    1.55
     cei
    1.31
    ทั้ง
    1.24
     los
    1.09
     těch
    1.05
    בעת
    1.04
     των
    0.98
    的三
    0.94
     årets
    0.93
    Activations Density 0.081%

    No Known Activations